Search

The audio watermarking technique embeds messages into audio and accurately extracts messages from the watermarked audio. Traditional methods develop algorithms based on expert experience to embed watermarks into the time-domain or transform-domain of signals. With the development of deep neural networks, deep learning-based neural audio watermarking has emerged. Compared to traditional algorithms, neural audio watermarking achieves better robustness by considering various attacks during training. However, current neural watermarking methods suffer from low capacity and unsatisfactory imperceptibility. Additionally, the issue of watermark locating, which is extremely important and even more pronounced in neural audio watermarking, has not been adequately studied. In this paper, we design a dual-embedding watermarking model for efficient locating. We also consider the impact of the attack layer on the invertible neural network in robustness training, improving the model to enhance both its reasonableness and stability. Experiments show that the proposed model, IDEAW, can withstand various attacks with higher capacity and more efficient locating ability compared to existing methods., Comment: Accepted by the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)

The rocketing prosperity of large language models (LLMs) in recent years has boosted the prevalence of vision-language models (VLMs) in the medical sector. In our online medical consultation scenario, a doctor responds to the texts and images provided by a patient in multiple rounds to diagnose her/his health condition, forming a multi-turn multimodal medical dialogue format. Unlike high-quality images captured by professional equipment in traditional medical visual question answering (Med-VQA), the images in our case are taken by patients' mobile phones. These images have poor quality control, with issues such as excessive background elements and the lesion area being significantly off-center, leading to degradation of vision-language alignment in the model training phase. In this paper, we propose ZALM3, a Zero-shot strategy to improve vision-language ALignment in Multi-turn Multimodal Medical dialogue. Since we observe that the preceding text conversations before an image can infer the regions of interest (RoIs) in the image, ZALM3 employs an LLM to summarize the keywords from the preceding context and a visual grounding model to extract the RoIs. The updated images eliminate unnecessary background noise and provide more effective vision-language alignment. To better evaluate our proposed method, we design a new subjective assessment metric for multi-turn unimodal/multimodal medical dialogue to provide a fine-grained performance comparison. Our experiments across three different clinical departments remarkably demonstrate the efficacy of ZALM3 with statistical significance.

Knowledge tracing is a technique that predicts students' future performance by analyzing their learning process through historical interactions with intelligent educational platforms, enabling a precise evaluation of their knowledge mastery. Recent studies have achieved significant progress by leveraging powerful deep neural networks. These models construct complex input representations using questions, skills, and other auxiliary information but overlook individual student characteristics, which limits the capability for personalized assessment. Additionally, the available datasets in the field exhibit class imbalance issues. The models that simply predict all responses as correct without substantial effort can yield impressive accuracy. In this paper, we propose PKT, a novel approach for personalized knowledge tracing. PKT reconstructs representations from sequences of interactions with a tutoring platform to capture latent information about the students. Moreover, PKT incorporates focal loss to improve prioritize minority classes, thereby achieving more balanced predictions. Extensive experimental results on four publicly available educational datasets demonstrate the advanced predictive performance of PKT in comparison with 16 state-of-the-art models. To ensure the reproducibility of our research, the code is publicly available at https://anonymous.4open.science/r/PKT.

Online Domain Adaptation (OnDA) is designed to handle unforeseeable domain changes at minimal cost that occur during the deployment of the model, lacking clear boundaries between the domain, such as sudden weather events. However, existing OnDA methods that rely solely on the model itself to adapt to the current domain often misidentify ambiguous classes amidst continuous domain shifts and pass on this erroneous knowledge to the next domain. To tackle this, we propose \textbf{RODASS}, a \textbf{R}obust \textbf{O}nline \textbf{D}omain \textbf{A}daptive \textbf{S}emantic \textbf{S}egmentation framework, which dynamically detects domain shifts and adjusts hyper-parameters to minimize training costs and error propagation. Specifically, we introduce the \textbf{D}ynamic \textbf{A}mbiguous \textbf{P}atch \textbf{Mask} (\textbf{DAP Mask}) strategy, which dynamically selects highly disturbed regions and masks these regions, mitigating error accumulation in ambiguous classes and enhancing the model's robustness against external noise in dynamic natural environments. Additionally, we present the \textbf{D}ynamic \textbf{S}ource \textbf{C}lass \textbf{Mix} (\textbf{DSC Mix}), a domain-aware mix method that augments target domain scenes with class-level source buffers, reducing the high uncertainty and noisy labels, thereby accelerating adaptation and offering a more efficient solution for online domain adaptation. Our approach outperforms state-of-the-art methods on widely used OnDA benchmarks while maintaining approximately 40 frames per second (FPS).

In the past two decades, the exploration of quantumness within Schwarzschild spacetime has garnered significant interest, particularly regarding the Hawking radiation's impact on quantum correlations and quantum coherence. Building on this foundation, we investigate how Hawking radiation influences maximal steered coherence (MSC)-a crucial measure for gauging the ability to generate coherence through steering. We find that as the Hawking temperature increases, the physically accessible MSC degrade while the unaccessible MSC increase. This observation is attributed to a redistribution of the initial quantum correlations, previously acknowledged by inertial observers, across all bipartite modes. In particular, we find that in limit case that the Hawking temperature tends to infinity, the accessible MSC equals to 1/\sqrt{2} of its initial value, and the unaccessible MSC also equals to the same value. Our findings illuminate the intricate dynamics of quantum information in the vicinity of black holes, suggesting that Hawking radiation plays a pivotal role in reshaping the landscape of quantum coherence and entanglement in curved spacetime. This study not only advances our theoretical understanding of black hole thermodynamics but also opens new avenues for investigating the interface between quantum mechanics and general relativity., Comment: 4 pages, 1 figure

Recent studies have increasingly focused on the effect of relativistic motion on quantum coherence. Prior research predominantly examined the influence of relative motion on basis-dependent quantum coherence, underscoring its susceptibility to decoherence under accelerated conditions. Yet, the effect of relativistic motion on basis-independent quantum coherence, which is critical for understanding the intrinsic quantum features of a system, remains an interesting open question. This paper addresses this question by examining how total, collective, and localized coherence are affected by acceleration and coupling strength. Our analysis reveals that both total and collective coherence significantly decrease with increasing acceleration and coupling strength, ultimately vanishing at high levels of acceleration. This underscores the profound impact of Unruh thermal noise. Conversely, localized coherence exhibits relative stability, decreasing to zero only under the extreme condition of infinite acceleration. Moreover, we demonstrate that collective, localized, and basis-independent coherence collectively satisfy the triangle inequality. These findings are crucial for enhancing our understanding of quantum information dynamics in environments subjected to high acceleration and offer valuable insights on the behavior of quantum coherence under relativistic conditions., Comment: 7 pages, 3 figures

Radio Frequency Fingerprint Identification (RFFI) has emerged as a pivotal task for reliable device authentication. Despite advancements in RFFI methods, background noise and intentional modulation features result in weak energy and subtle differences in the RFF features. These challenges diminish the capability of RFFI methods in feature representation, complicating the effective identification of device identities. This paper proposes a novel Multi-Periodicity Dependency Transformer (MPDFormer) to address these challenges. The MPDFormer employs a spectrum offset-based periodic embedding representation to augment the discrepency of intrinsic features. We delve into the intricacies of the periodicity-dependency attention mechanism, integrating both inter-period and intra-period attention mechanisms. This mechanism facilitates the extraction of both long and short-range periodicity-dependency features , accentuating the feature distinction whilst concurrently attenuating the perturbations caused by background noise and weak-periodicity features. Empirical results demonstrate MPDFormer's superiority over established baseline methods, achieving a 0.07s inference time on NVIDIA Jetson Orin NX.

Higher-order community detection (HCD) reveals both mesoscale structures and functional characteristics of real-life networks. Although many methods have been developed from diverse perspectives, to our knowledge, none can provide fine-grained higher-order fuzzy community information. This study presents a novel concept of higher-order fuzzy memberships that quantify the membership grades of motifs to crisp higher-order communities, thereby revealing the partial community affiliations. Furthermore, we employ higher-order fuzzy memberships to enhance HCD via a general framework called fuzzy memberships assisted motif-based evolutionary modularity (FMMEM). In FFMEM, on the one hand, a fuzzy membership-based neighbor community modification (FM-NCM) strategy is designed to correct misassigned bridge nodes, thereby improving partition quality. On the other hand, a fuzzy membership-based local community merging (FM-LCM) strategy is also proposed to combine excessively fragmented communities for enhancing local search ability. Experimental results indicate that the FMMEM framework outperforms state-of-the-art methods in both synthetic and real-world datasets, particularly in the networks with ambiguous and complex structures., Comment: 12 pages, 6 figures

Controllability and proactivity are crucial properties of autonomous conversational agents (CAs). Controllability requires the CAs to follow the standard operating procedures (SOPs), such as verifying identity before activating credit cards. Proactivity requires the CAs to guide the conversation towards the goal during user uncooperation, such as persuasive dialogue. Existing research cannot be unified with controllability, proactivity, and low manual annotation. To bridge this gap, we propose a new framework for planning-based conversational agents (PCA) powered by large language models (LLMs), which only requires humans to define tasks and goals for the LLMs. Before conversation, LLM plans the core and necessary SOP for dialogue offline. During the conversation, LLM plans the best action path online referring to the SOP, and generates responses to achieve process controllability. Subsequently, we propose a semi-automatic dialogue data creation framework and curate a high-quality dialogue dataset (PCA-D). Meanwhile, we develop multiple variants and evaluation metrics for PCA, e.g., planning with Monte Carlo Tree Search (PCA-M), which searches for the optimal dialogue action while satisfying SOP constraints and achieving the proactive of the dialogue. Experiment results show that LLMs finetuned on PCA-D can significantly improve the performance and generalize to unseen domains. PCA-M outperforms other CoT and ToT baselines in terms of conversation controllability, proactivity, task success rate, and overall logical coherence, and is applicable in industry dialogue scenarios. The dataset and codes are available at XXXX.

Purpose: To evaluate the performance of an automated deep learning method in detecting ascites and subsequently quantifying its volume in patients with liver cirrhosis and ovarian cancer. Materials and Methods: This retrospective study included contrast-enhanced and non-contrast abdominal-pelvic CT scans of patients with cirrhotic ascites and patients with ovarian cancer from two institutions, National Institutes of Health (NIH) and University of Wisconsin (UofW). The model, trained on The Cancer Genome Atlas Ovarian Cancer dataset (mean age, 60 years +/- 11 [s.d.]; 143 female), was tested on two internal (NIH-LC and NIH-OV) and one external dataset (UofW-LC). Its performance was measured by the Dice coefficient, standard deviations, and 95% confidence intervals, focusing on ascites volume in the peritoneal cavity. Results: On NIH-LC (25 patients; mean age, 59 years +/- 14 [s.d.]; 14 male) and NIH-OV (166 patients; mean age, 65 years +/- 9 [s.d.]; all female), the model achieved Dice scores of 0.855 +/- 0.061 (CI: 0.831-0.878) and 0.826 +/- 0.153 (CI: 0.764-0.887), with median volume estimation errors of 19.6% (IQR: 13.2-29.0) and 5.3% (IQR: 2.4-9.7) respectively. On UofW-LC (124 patients; mean age, 46 years +/- 12 [s.d.]; 73 female), the model had a Dice score of 0.830 +/- 0.107 (CI: 0.798-0.863) and median volume estimation error of 9.7% (IQR: 4.5-15.1). The model showed strong agreement with expert assessments, with r^2 values of 0.79, 0.98, and 0.97 across the test sets. Conclusion: The proposed deep learning method performed well in segmenting and quantifying the volume of ascites in concordance with expert radiologist assessments.

This paper introduces a novel privacy-preservation framework named PFID for LLMs that addresses critical privacy concerns by localizing user data through model sharding and singular value decomposition. When users are interacting with LLM systems, their prompts could be subject to being exposed to eavesdroppers within or outside LLM system providers who are interested in collecting users' input. In this work, we proposed a framework to camouflage user input, so as to alleviate privacy issues. Our framework proposes to place model shards on the client and the public server, we sent compressed hidden states instead of prompts to and from servers. Clients have held back information that can re-privatized the hidden states so that overall system performance is comparable to traditional LLMs services. Our framework was designed to be communication efficient, computation can be delegated to the local client so that the server's computation burden can be lightened. We conduct extensive experiments on machine translation tasks to verify our framework's performance., Comment: Submitted to EMNLP2024

Non-autoregressive (NAR) automatic speech recognition (ASR) models predict tokens independently and simultaneously, bringing high inference speed. However, there is still a gap in the accuracy of the NAR models compared to the autoregressive (AR) models. In this paper, we propose a single-step NAR ASR architecture with high accuracy and inference speed, called EffectiveASR. It uses an Index Mapping Vector (IMV) based alignment generator to generate alignments during training, and an alignment predictor to learn the alignments for inference. It can be trained end-to-end (E2E) with cross-entropy loss combined with alignment loss. The proposed EffectiveASR achieves competitive results on the AISHELL-1 and AISHELL-2 Mandarin benchmarks compared to the leading models. Specifically, it achieves character error rates (CER) of 4.26%/4.62% on the AISHELL-1 dev/test dataset, which outperforms the AR Conformer with about 30x inference speedup., Comment: Submitted to ICASSP 2025

The purpose of emotion recognition in conversation (ERC) is to identify the emotion category of an utterance based on contextual information. Previous ERC methods relied on simple connections for cross-modal fusion and ignored the information differences between modalities, resulting in the model being unable to focus on modality-specific emotional information. At the same time, the shared information between modalities was not processed to generate emotions. Information redundancy problem. To overcome these limitations, we propose a cross-modal fusion emotion prediction network based on vector connections. The network mainly includes two stages: the multi-modal feature fusion stage based on connection vectors and the emotion classification stage based on fused features. Furthermore, we design a supervised inter-class contrastive learning module based on emotion labels. Experimental results confirm the effectiveness of the proposed method, demonstrating excellent performance on the IEMOCAP and MELD datasets., Comment: Accepted by the 20th International Conference on Intelligent Computing (ICIC 2024)

Although current Text-To-Speech (TTS) models are able to generate high-quality speech samples, there are still challenges in developing emotion intensity controllable TTS. Most existing TTS models achieve emotion intensity control by extracting intensity information from reference speeches. Unfortunately, limited by the lack of modeling for intra-class emotion intensity and the model's information decoupling capability, the generated speech cannot achieve fine-grained emotion intensity control and suffers from information leakage issues. In this paper, we propose an emotion transfer TTS model, which defines a remapping-based sorting method to model intra-class relative intensity information, combined with Mutual Information (MI) to decouple speaker and emotion information, and synthesizes expressive speeches with perceptible intensity differences. Experiments show that our model achieves fine-grained emotion control while preserving speaker information., Comment: Accepted by the 8th APWeb-WAIM International Joint Conference on Web and Big Data

Known for efficient computation and easy storage, hashing has been extensively explored in cross-modal retrieval. The majority of current hashing models are predicated on the premise of a direct one-to-one mapping between data points. However, in real practice, data correspondence across modalities may be partially provided. In this research, we introduce an innovative unsupervised hashing technique designed for semi-paired cross-modal retrieval tasks, named Reconstruction Relations Embedded Hashing (RREH). RREH assumes that multi-modal data share a common subspace. For paired data, RREH explores the latent consistent information of heterogeneous modalities by seeking a shared representation. For unpaired data, to effectively capture the latent discriminative features, the high-order relationships between unpaired data and anchors are embedded into the latent subspace, which are computed by efficient linear reconstruction. The anchors are sampled from paired data, which improves the efficiency of hash learning. The RREH trains the underlying features and the binary encodings in a unified framework with high-order reconstruction relations preserved. With the well devised objective function and discrete optimization algorithm, RREH is designed to be scalable, making it suitable for large-scale datasets and facilitating efficient cross-modal retrieval. In the evaluation process, the proposed is tested with partially paired data to establish its superiority over several existing methods., Comment: Accepted by the 20th International Conference on Intelligent Computing (ICIC 2024)

With the rapid advancements in artificial intelligence, the development of knowledgeable and personalized agents has become increasingly prevalent. However, the inherent variability in state variables and action spaces among personalized agents poses significant aggregation challenges for traditional federated learning algorithms. To tackle these challenges, we introduce the Federated Split Decision Transformer (FSDT), an innovative framework designed explicitly for AI agent decision tasks. The FSDT framework excels at navigating the intricacies of personalized agents by harnessing distributed data for training while preserving data privacy. It employs a two-stage training process, with local embedding and prediction models on client agents and a global transformer decoder model on the server. Our comprehensive evaluation using the benchmark D4RL dataset highlights the superior performance of our algorithm in federated split learning for personalized agents, coupled with significant reductions in communication and computational overhead compared to traditional centralized training approaches. The FSDT framework demonstrates strong potential for enabling efficient and privacy-preserving collaborative learning in applications such as autonomous driving decision systems. Our findings underscore the efficacy of the FSDT framework in effectively leveraging distributed offline reinforcement learning data to enable powerful multi-type agent decision systems., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

In pursuit of quantum advancements across disciplines, a bright and coherent electron source is expected to be a cornerstone of diverse applications including electron microscopy, laser accelerators, and free electron lasers. Current cathodes, such as cold field and photoemission, can generate high-quality electron beams with different cathode materials, geometric configurations, and laser excitation profiles, but their maintenance of both quantum coherence and high beam brightness suffers from the space-charge repulsion of many electrons. Here, we propose a new mechanism to provide collective emission of coherent electrons based on Auger photoemission. Our approach leverages a photon-induced four-level Auger process that necessitates a combination of photoemission and Auger recombination. The Auger electrons, energized through a recycling process of photoelectrons, emit collectively into the vacuum as secondary electrons. We compare coherent and incoherent Auger photoemission, identifying that the working condition of the coherent photoemission requires population inversion, akin to the four-level laser system. Our work provides insights for experimental realization and nanofabrication of Auger photocathodes, addressing a critical need in advancing quantum technologies relating to correlated coherent sources., Comment: 12 pages, 2 figures

Most earlier investigations on talking face generation have focused on the synchronization of lip motion and speech content. However, human head pose and facial emotions are equally important characteristics of natural human faces. While audio-driven talking face generation has seen notable advancements, existing methods either overlook facial emotions or are limited to specific individuals and cannot be applied to arbitrary subjects. In this paper, we propose a one-shot Talking Head Generation framework (SPEAK) that distinguishes itself from general Talking Face Generation by enabling emotional and postural control. Specifically, we introduce the Inter-Reconstructed Feature Disentanglement (IRFD) method to decouple human facial features into three latent spaces. We then design a face editing module that modifies speech content and facial latent codes into a single latent space. Subsequently, we present a novel generator that employs modified latent codes derived from the editing module to regulate emotional expression, head poses, and speech content in synthesizing facial animations. Extensive trials demonstrate that our method can generate realistic talking head with coordinated lip motions, authentic facial emotions, and smooth head movements. The demo video is available at the anonymous link: https://anonymous.4open.science/r/SPEAK-F56E, Comment: Due to our negligence, there are factual errors in the experimental results, so we are considering resubmitting the paper after an overhaul

One-shot voice conversion aims to change the timbre of any source speech to match that of the unseen target speaker with only one speech sample. Existing methods face difficulties in satisfactory speech representation disentanglement and suffer from sizable networks as some of them leverage numerous complex modules for disentanglement. In this paper, we propose a model named MAIN-VC to effectively disentangle via a concise neural network. The proposed model utilizes Siamese encoders to learn clean representations, further enhanced by the designed mutual information estimator. The Siamese structure and the newly designed convolution module contribute to the lightweight of our model while ensuring performance in diverse voice conversion tasks. The experimental results show that the proposed model achieves comparable subjective scores and exhibits improvements in objective metrics compared to existing methods in a one-shot voice conversion scenario., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

Voice conversion is the task to transform voice characteristics of source speech while preserving content information. Nowadays, self-supervised representation learning models are increasingly utilized in content extraction. However, in these representations, a lot of hidden speaker information leads to timbre leakage while the prosodic information of hidden units lacks use. To address these issues, we propose a novel framework for expressive voice conversion called "SAVC" based on soft speech units from HuBert-soft. Taking soft speech units as input, we design an attribute encoder to extract content and prosody features respectively. Specifically, we first introduce statistic perturbation imposed by adversarial style augmentation to eliminate speaker information. Then the prosody is implicitly modeled on soft speech units with knowledge distillation. Experiment results show that the intelligibility and naturalness of converted speech outperform previous work., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

Extractive Question Answering (EQA) in Machine Reading Comprehension (MRC) often faces the challenge of dealing with semantically identical but format-variant inputs. Our work introduces a novel approach, called the ``Query Latent Semantic Calibrator (QLSC)'', designed as an auxiliary module for existing MRC models. We propose a unique scaling strategy to capture latent semantic center features of queries. These features are then seamlessly integrated into traditional query and passage embeddings using an attention mechanism. By deepening the comprehension of the semantic queries-passage relationship, our approach diminishes sensitivity to variations in text format and boosts the model's capability in pinpointing accurate answers. Experimental results on robust Question-Answer datasets confirm that our approach effectively handles format-variant but semantically identical queries, highlighting the effectiveness and adaptability of our proposed method., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

Using unsupervised learning to disentangle speech into content, rhythm, pitch, and timbre for voice conversion has become a hot research topic. Existing works generally take into account disentangling speech components through human-crafted bottleneck features which can not achieve sufficient information disentangling, while pitch and rhythm may still be mixed together. There is a risk of information overlap in the disentangling process which results in less speech naturalness. To overcome such limits, we propose a two-stage model to disentangle speech representations in a self-supervised manner without a human-crafted bottleneck design, which uses the Mutual Information (MI) with the designed upper bound estimator (IFUB) to separate overlapping information between speech components. Moreover, we design a Joint Text-Guided Consistent (TGC) module to guide the extraction of speech content and eliminate timbre leakage issues. Experiments show that our model can achieve a better performance than the baseline, regarding disentanglement effectiveness, speech naturalness, and similarity. Audio samples can be found at https://largeaudiomodel.com/eadvc., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

In recent years, Transformer networks have shown remarkable performance in speech recognition tasks. However, their deployment poses challenges due to high computational and storage resource requirements. To address this issue, a lightweight model called EfficientASR is proposed in this paper, aiming to enhance the versatility of Transformer models. EfficientASR employs two primary modules: Shared Residual Multi-Head Attention (SRMHA) and Chunk-Level Feedforward Networks (CFFN). The SRMHA module effectively reduces redundant computations in the network, while the CFFN module captures spatial knowledge and reduces the number of parameters. The effectiveness of the EfficientASR model is validated on two public datasets, namely Aishell-1 and HKUST. Experimental results demonstrate a 36% reduction in parameters compared to the baseline Transformer network, along with improvements of 0.3% and 0.2% in Character Error Rate (CER) on the Aishell-1 and HKUST datasets, respectively., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

Singing voice beautifying is a novel task that has application value in people's daily life, aiming to correct the pitch of the singing voice and improve the expressiveness without changing the original timbre and content. Existing methods rely on paired data or only concentrate on the correction of pitch. However, professional songs and amateur songs from the same person are hard to obtain, and singing voice beautifying doesn't only contain pitch correction but other aspects like emotion and rhythm. Since we propose a fast and high-fidelity singing voice beautifying system called ConTuner, a diffusion model combined with the modified condition to generate the beautified Mel-spectrogram, where the modified condition is composed of optimized pitch and expressiveness. For pitch correction, we establish a mapping relationship from MIDI, spectrum envelope to pitch. To make amateur singing more expressive, we propose the expressiveness enhancer in the latent space to convert amateur vocal tone to professional. ConTuner achieves a satisfactory beautification effect on both Mandarin and English songs. Ablation study demonstrates that the expressiveness enhancer and generator-based accelerate method in ConTuner are effective., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

Single-model systems often suffer from deficiencies in tasks such as speaker verification (SV) and image classification, relying heavily on partial prior knowledge during decision-making, resulting in suboptimal performance. Although multi-model fusion (MMF) can mitigate some of these issues, redundancy in learned representations may limits improvements. To this end, we propose an adversarial complementary representation learning (ACoRL) framework that enables newly trained models to avoid previously acquired knowledge, allowing each individual component model to learn maximally distinct, complementary representations. We make three detailed explanations of why this works and experimental results demonstrate that our method more efficiently improves performance compared to traditional MMF. Furthermore, attribution analysis validates the model trained under ACoRL acquires more complementary knowledge, highlighting the efficacy of our approach in enhancing efficiency and robustness across tasks., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

With recent advances in speech synthesis including text-to-speech (TTS) and voice conversion (VC) systems enabling the generation of ultra-realistic audio deepfakes, there is growing concern about their potential misuse. However, most deepfake (DF) detection methods rely solely on the fuzzy knowledge learned by a single model, resulting in performance bottlenecks and transparency issues. Inspired by retrieval-augmented generation (RAG), we propose a retrieval-augmented detection (RAD) framework that augments test samples with similar retrieved samples for enhanced detection. We also extend the multi-fusion attentive classifier to integrate it with our proposed RAD framework. Extensive experiments show the superior performance of the proposed RAD framework over baseline methods, achieving state-of-the-art results on the ASVspoof 2021 DF set and competitive results on the 2019 and 2021 LA sets. Further sample analysis indicates that the retriever consistently retrieves samples mostly from the same speaker with acoustic characteristics highly consistent with the query audio, thereby improving detection performance., Comment: Accepted by the 2024 International Conference on Multimedia Retrieval (ICMR 2024)

Knowledge Graph Completion (KGC) has emerged as a promising solution to address the issue of incompleteness within Knowledge Graphs (KGs). Traditional KGC research primarily centers on triple classification and link prediction. Nevertheless, we contend that these tasks do not align well with real-world scenarios and merely serve as surrogate benchmarks. In this paper, we investigate three crucial processes relevant to real-world construction scenarios: (a) the verification process, which arises from the necessity and limitations of human verifiers; (b) the mining process, which identifies the most promising candidates for verification; and (c) the training process, which harnesses verified data for subsequent utilization; in order to achieve a transition toward more realistic challenges. By integrating these three processes, we introduce the Progressive Knowledge Graph Completion (PKGC) task, which simulates the gradual completion of KGs in real-world scenarios. Furthermore, to expedite PKGC processing, we propose two acceleration modules: Optimized Top-$k$ algorithm and Semantic Validity Filter. These modules significantly enhance the efficiency of the mining procedure. Our experiments demonstrate that performance in link prediction does not accurately reflect performance in PKGC. A more in-depth analysis reveals the key factors influencing the results and provides potential directions for future research., Comment: 14 pages, 10 figures

Negative refractive index (NRI) of the mescopic dissipative left-handed transmission line (LHTL) is manipulated by the displaced squeezed Fock state (DSFS) and the dissipation presented by the resistance and conductance. Comparing to the classical LHTL, some specific quantum characteristics are shown in the LHTL because of quantum effect, which will be significant to its miniaturization application in microwave frequency., Comment: 5 pages, 4 figures

Intent is defined for understanding spoken language in existing works. Both textual features and acoustic features involved in medical speech contain intent, which is important for symptomatic diagnosis. In this paper, we propose a medical speech classification model named DRSC that automatically learns to disentangle intent and content representations from textual-acoustic data for classification. The intent representations of the text domain and the Mel-spectrogram domain are extracted via intent encoders, and then the reconstructed text feature and the Mel-spectrogram feature are obtained through two exchanges. After combining the intent from two domains into a joint representation, the integrated intent representation is fed into a decision layer for classification. Experimental results show that our model obtains an average accuracy rate of 95% in detecting 25 different medical symptoms., Comment: Accepted by the 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD 2024)

Left-handedness signifies negative permittivity ($\varepsilon_r$) and permeability ((\mu_r)) in the same frequency band. The $\varepsilon_r$ and $\mu_r$ are evaluated in a quantized composite right-left handed transmission line (CRLH-TL), and the frequency band for left-handedness is also valuated in the balanced resonance ($ L_r C_l = L_l C_r $) and unbalanced resonance($L_l C_r \neq L_r C_l$) cases in the displaced squeezed Fock state. The results show that the balanced resonance plays an important role in bandwidth and achieving for left-handedness. These displays some quantum mechanical behaviors and proposes a new potential approach to wider frequency band left-handedness for the quantized CRLH-TL., Comment: 10 pages, 3 figures

Dance serves as a powerful medium for expressing human emotions, but the lifelike generation of dance is still a considerable challenge. Recently, diffusion models have showcased remarkable generative abilities across various domains. They hold promise for human motion generation due to their adaptable many-to-many nature. Nonetheless, current diffusion-based motion generation models often create entire motion sequences directly and unidirectionally, lacking focus on the motion with local and bidirectional enhancement. When choreographing high-quality dance movements, people need to take into account not only the musical context but also the nearby music-aligned dance motions. To authentically capture human behavior, we propose a Bidirectional Autoregressive Diffusion Model (BADM) for music-to-dance generation, where a bidirectional encoder is built to enforce that the generated dance is harmonious in both the forward and backward directions. To make the generated dance motion smoother, a local information decoder is built for local motion enhancement. The proposed framework is able to generate new motions based on the input conditions and nearby motions, which foresees individual motion slices iteratively and consolidates all predictions. To further refine the synchronicity between the generated dance and the beat, the beat information is incorporated as an input to generate better music-aligned dance movements. Experimental results demonstrate that the proposed model achieves state-of-the-art performance compared to existing unidirectional approaches on the prominent benchmark for music-to-dance generation.

Deploying neural networks on microcontroller units (MCUs) presents substantial challenges due to their constrained computation and memory resources. Previous researches have explored patch-based inference as a strategy to conserve memory without sacrificing model accuracy. However, this technique suffers from severe redundant computation overhead, leading to a substantial increase in execution latency. A feasible solution to address this issue is mixed-precision quantization, but it faces the challenges of accuracy degradation and a time-consuming search time. In this paper, we propose QuantMCU, a novel patch-based inference method that utilizes value-driven mixed-precision quantization to reduce redundant computation. We first utilize value-driven patch classification (VDPC) to maintain the model accuracy. VDPC classifies patches into two classes based on whether they contain outlier values. For patches containing outlier values, we apply 8-bit quantization to the feature maps on the dataflow branches that follow. In addition, for patches without outlier values, we utilize value-driven quantization search (VDQS) on the feature maps of their following dataflow branches to reduce search time. Specifically, VDQS introduces a novel quantization search metric that takes into account both computation and accuracy, and it employs entropy as an accuracy representation to avoid additional training. VDQS also adopts an iterative approach to determine the bitwidth of each feature map to further accelerate the search process. Experimental results on real-world MCU devices show that QuantMCU can reduce computation by 2.2x on average while maintaining comparable model accuracy compared to the state-of-the-art patch-based inference methods., Comment: Accepted by the 27th Design, Automation and Test in Europe Conference (DATE 2024)

This paper introduces INCPrompt, an innovative continual learning solution that effectively addresses catastrophic forgetting. INCPrompt's key innovation lies in its use of adaptive key-learner and task-aware prompts that capture task-relevant information. This unique combination encapsulates general knowledge across tasks and encodes task-specific knowledge. Our comprehensive evaluation across multiple continual learning benchmarks demonstrates INCPrompt's superiority over existing algorithms, showing its effectiveness in mitigating catastrophic forgetting while maintaining high performance. These results highlight the significant impact of task-aware incremental prompting on continual learning performance., Comment: Accepted by the 49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)

Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance degradation when these agents face new tasks. In our work, we propose a novel solution - the Progressive Prompt Decision Transformer (P2DT). This method enhances a transformer-based model by dynamically appending decision tokens during new task training, thus fostering task-specific policies. Our approach mitigates forgetting in continual and offline reinforcement learning scenarios. Moreover, P2DT leverages trajectories collected via traditional reinforcement learning from all tasks and generates new task-specific tokens during training, thereby retaining knowledge from previous studies. Preliminary results demonstrate that our model effectively alleviates catastrophic forgetting and scales well with increasing task environments., Comment: Accepted by the 49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)

Gamma-ray Transient Monitor (GTM) is an all-sky monitor onboard the Distant Retrograde Orbit-A (DRO-A) satellite with the scientific objective of detecting gamma-ray transients ranging from 20 keV to 1 MeV. GTM is equipped with 5 Gamma-ray Transient Probe (GTP) detector modules, utilizing the NaI(Tl) scintillator coupled with a SiPM array. To reduce the SiPM noise, GTP makes use of a dedicated dual-channel coincident readout design. In this work, we firstly studied the impact of different coincidence times on detection efficiency and ultimately selected the 500 ns time coincidence window for offline data processing. To test the performance of GTPs and validate the Monte Carlo simulated energy response, we conducted comprehensive ground calibration tests using Hard X-ray Calibration Facility (HXCF) and radioactive sources, including energy response, detection efficiency, spatial response, bias-voltage response, and temperature dependence. We extensively presented the ground calibration results, and validated the design and mass model of GTP detector. These work paved the road for the in-flight observation and science data analysis., Comment: 15 pages, 25 figures

The GECAM series of satellites utilize LaBr3(Ce), LaBr3(Ce,Sr), and NaI(Tl) crystals as sensitive materials for gamma-ray detectors (GRDs). To investigate the non-linearity in the detection of low-energy gamma rays and address errors in the E-C relationship calibration, comprehensive tests and comparative studies of the non-linearity of these three crystals were conducted using Compton electrons, radioactive sources, and mono-energetic X-rays. The non-linearity test results for Compton electrons and X-rays displayed substantial differences, with all three crystals showing higher non-linearity for X-rays and gamma-rays than for Compton electrons. Despite LaBr3(Ce) and LaBr3(Ce,Sr) crystals having higher absolute light yields, they exhibited a noticeable non-linear decrease in light yield, especially at energies below 400 keV. The NaI(Tl) crystal demonstrated excess light output in the 6~200 keV range, reaching a maximum excess of 9.2% at 30 keV in X-ray testing and up to 15.5% at 14 keV during Compton electron testing, indicating a significant advantage in the detection of low-energy gamma rays. Furthermore, this paper explores the underlying causes of the observed non-linearity in these crystals. This study not only elucidates the detector responses of GECAM, but also marks the inaugural comprehensive investigation into the non-linearity of domestically produced lanthanum bromide and sodium iodide crystals., Comment: 12pages, 16 figures

Loop closure is necessary for correcting errors accumulated in simultaneous localization and mapping (SLAM) in unknown environments. However, conventional loop closure methods based on low-level geometric or image features may cause high ambiguity by not distinguishing similar scenarios. Thus, incorrect loop closures can occur. Though semantic 2D image information is considered in some literature to detect loop closures, there is little work that compares 3D scenes as an integral part of a semantic SLAM system. This paper introduces an approach, called SmSLAM+LCD, integrated into a semantic SLAM system to combine high-level 3D semantic information and low-level feature information to conduct accurate loop closure detection and effective drift reduction. The effectiveness of our approach is demonstrated in testing results.

Detecting out-of-distribution (OOD) examples is crucial to guarantee the reliability and safety of deep neural networks in real-world settings. In this paper, we offer an innovative perspective on quantifying the disparities between in-distribution (ID) and OOD data -- analyzing the uncertainty that arises when models attempt to explain their predictive decisions. This perspective is motivated by our observation that gradient-based attribution methods encounter challenges in assigning feature importance to OOD data, thereby yielding divergent explanation patterns. Consequently, we investigate how attribution gradients lead to uncertain explanation outcomes and introduce two forms of abnormalities for OOD detection: the zero-deflation abnormality and the channel-wise average abnormality. We then propose GAIA, a simple and effective approach that incorporates Gradient Abnormality Inspection and Aggregation. The effectiveness of GAIA is validated on both commonly utilized (CIFAR) and large-scale (ImageNet-1k) benchmarks. Specifically, GAIA reduces the average FPR95 by 23.10% on CIFAR10 and by 45.41% on CIFAR100 compared to advanced post-hoc methods., Comment: Accepted by NeurIPS2023

Most existing neural-based text-to-speech methods rely on extensive datasets and face challenges under low-resource condition. In this paper, we introduce a novel semi-supervised text-to-speech synthesis model that learns from both paired and unpaired data to address this challenge. The key component of the proposed model is a dynamic quantized representation module, which is integrated into a sequential autoencoder. When given paired data, the module incorporates a trainable codebook that learns quantized representations under the supervision of the paired data. However, due to the limited paired data in low-resource scenario, these paired data are difficult to cover all phonemes. Then unpaired data is fed to expand the dynamic codebook by adding quantized representation vectors that are sufficiently distant from the existing ones during training. Experiments show that with less than 120 minutes of paired data, the proposed method outperforms existing methods in both subjective and objective metrics., Comment: Accepted by the 13th IEEE International Conference on Big Data and Cloud Computing (IEEE BDCloud 2023)

This paper proposes a talking face generation method named "CP-EB" that takes an audio signal as input and a person image as reference, to synthesize a photo-realistic people talking video with head poses controlled by a short video clip and proper eye blinking embedding. It's noted that not only the head pose but also eye blinking are both important aspects for deep fake detection. The implicit control of poses by video has already achieved by the state-of-art work. According to recent research, eye blinking has weak correlation with input audio which means eye blinks extraction from audio and generation are possible. Hence, we propose a GAN-based architecture to extract eye blink feature from input audio and reference video respectively and employ contrastive training between them, then embed it into the concatenated features of identity and poses to generate talking face images. Experimental results show that the proposed method can generate photo-realistic talking face with synchronous lips motions, natural head poses and blinking eyes., Comment: Accepted by the 21st IEEE International Symposium on Parallel and Distributed Processing with Applications (IEEE ISPA 2023)

Better disentanglement of speech representation is essential to improve the quality of voice conversion. Recently contrastive learning is applied to voice conversion successfully based on speaker labels. However, the performance of model will reduce in conversion between similar speakers. Hence, we propose an augmented negative sample selection to address the issue. Specifically, we create hard negative samples based on the proposed speaker fusion module to improve learning ability of speaker encoder. Furthermore, considering the fine-grain modeling of speaker style, we employ a reference encoder to extract fine-grained style and conduct the augmented contrastive learning on global style. The experimental results show that the proposed method outperforms previous work in voice conversion tasks., Comment: Accepted by the 21st IEEE International Symposium on Parallel and Distributed Processing with Applications (IEEE ISPA 2023)

The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator. The generator formulates the answer based on the documents retrieved by the retriever. Incorporating Large Language Models (LLMs) as generators is beneficial due to their advanced QA capabilities, but they are typically too large to be fine-tuned with budget constraints while some of them are only accessible via APIs. To tackle this issue and further improve ReQA performance, we propose a trainable Pluggable Reward-Driven Contextual Adapter (PRCA), keeping the generator as a black box. Positioned between the retriever and generator in a Pluggable manner, PRCA refines the retrieved information by operating in a token-autoregressive strategy via maximizing rewards of the reinforcement learning phase. Our experiments validate PRCA's effectiveness in enhancing ReQA performance on three datasets by up to 20% improvement to fit black-box LLMs into existing frameworks, demonstrating its considerable potential in the LLMs era., Comment: Accepted by the Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. (EMNLP2023)

Speaker verification (SV) performance deteriorates as utterances become shorter. To this end, we propose a new architecture called VoiceExtender which provides a promising solution for improving SV performance when handling short-duration speech signals. We use two guided diffusion models, the built-in and the external speaker embedding (SE) guided diffusion model, both of which utilize a diffusion model-based sample generator that leverages SE guidance to augment the speech features based on a short utterance. Extensive experimental results on the VoxCeleb1 dataset show that our method outperforms the baseline, with relative improvements in equal error rate (EER) of 46.1%, 35.7%, 10.4%, and 5.7% for the short utterance conditions of 0.5, 1.0, 1.5, and 2.0 seconds, respectively., Comment: Accepted by the 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2023)

Bilinear based models are powerful and widely used approaches for Knowledge Graphs Completion (KGC). Although bilinear based models have achieved significant advances, these studies mainly concentrate on posterior properties (based on evidence, e.g. symmetry pattern) while neglecting the prior properties. In this paper, we find a prior property named "the law of identity" that cannot be captured by bilinear based models, which hinders them from comprehensively modeling the characteristics of KGs. To address this issue, we introduce a solution called Unit Ball Bilinear Model (UniBi). This model not only achieves theoretical superiority but also offers enhanced interpretability and performance by minimizing ineffective learning through minimal constraints. Experiments demonstrate that UniBi models the prior property and verify its interpretability and performance.

This work addresses the problem of online exploration and visual sensor coverage of unknown environments. We introduce a novel perception roadmap we refer to as the Active Perception Network (APN) that serves as a hierarchical topological graph describing how to traverse and perceive an incrementally built spatial map of the environment. The APN state is incrementally updated to expand a connected configuration space that extends throughout as much of the known space as possible, using efficient difference-awareness techniques that track the discrete changes of the spatial map to inform the updates. A frontier-guided approach is presented for efficient evaluation of information gain and covisible information, which guides view sampling and refinement to ensure maximum coverage of the unmapped space is maintained within the APN. The updated roadmap is hierarchically decomposed into subgraph regions which we use to facilitate a non-myopic global view sequence planner. A comparative analysis to several state-of-the-art approaches was conducted, showing significant performance improvements in terms of total exploration time and surface coverage, and demonstrating high computational efficiency that is scalable to large and complex environments., Comment: 19 pages, 10 figures

Cross-modal retrieval (CMR) has been extensively applied in various domains, such as multimedia search engines and recommendation systems. Most existing CMR methods focus on image-to-text retrieval, whereas audio-to-text retrieval, a less explored domain, has posed a great challenge due to the difficulty to uncover discriminative features from audio clips and texts. Existing studies are restricted in the following two ways: 1) Most researchers utilize contrastive learning to construct a common subspace where similarities among data can be measured. However, they considers only cross-modal transformation, neglecting the intra-modal separability. Besides, the temperature parameter is not adaptively adjusted along with semantic guidance, which degrades the performance. 2) These methods do not take latent representation reconstruction into account, which is essential for semantic alignment. This paper introduces a novel audio-text oriented CMR approach, termed Contrastive Latent Space Reconstruction Learning (CLSR). CLSR improves contrastive representation learning by taking intra-modal separability into account and adopting an adaptive temperature control strategy. Moreover, the latent representation reconstruction modules are embedded into the CMR framework, which improves modal interaction. Experiments in comparison with some state-of-the-art methods on two audio-text datasets have validated the superiority of CLSR., Comment: Accepted by The 35th IEEE International Conference on Tools with Artificial Intelligence. (ICTAI 2023)

This paper integrates graph-to-sequence into an end-to-end text-to-speech framework for syntax-aware modelling with syntactic information of input text. Specifically, the input text is parsed by a dependency parsing module to form a syntactic graph. The syntactic graph is then encoded by a graph encoder to extract the syntactic hidden information, which is concatenated with phoneme embedding and input to the alignment and flow-based decoding modules to generate the raw audio waveform. The model is experimented on two languages, English and Mandarin, using single-speaker, few samples of target speakers, and multi-speaker datasets, respectively. Experimental results show better prosodic consistency performance between input text and generated audio, and also get higher scores in the subjective prosodic evaluation, and show the ability of voice conversion. Besides, the efficiency of the model is largely boosted through the design of the AI chip operator with 5x acceleration., Comment: Accepted by The 35th IEEE International Conference on Tools with Artificial Intelligence. (ICTAI 2023)

Most existing sandstorm image enhancement methods are based on traditional theory and prior knowledge, which often restrict their applicability in real-world scenarios. In addition, these approaches often adopt a strategy of color correction followed by dust removal, which makes the algorithm structure too complex. To solve the issue, we introduce a novel image restoration model, named all-in-one sandstorm removal network (AOSR-Net). This model is developed based on a re-formulated sandstorm scattering model, which directly establishes the image mapping relationship by integrating intermediate parameters. Such integration scheme effectively addresses the problems of over-enhancement and weak generalization in the field of sand dust image enhancement. Experimental results on synthetic and real-world sandstorm images demonstrate the superiority of the proposed AOSR-Net over state-of-the-art (SOTA) algorithms., Comment: Accepted by The 35th IEEE International Conference on Tools with Artificial Intelligence. (ICTAI 2023)

Generating realistic talking faces is a complex and widely discussed task with numerous applications. In this paper, we present DiffTalker, a novel model designed to generate lifelike talking faces through audio and landmark co-driving. DiffTalker addresses the challenges associated with directly applying diffusion models to audio control, which are traditionally trained on text-image pairs. DiffTalker consists of two agent networks: a transformer-based landmarks completion network for geometric accuracy and a diffusion-based face generation network for texture details. Landmarks play a pivotal role in establishing a seamless connection between the audio and image domains, facilitating the incorporation of knowledge from pre-trained diffusion models. This innovative approach efficiently produces articulate-speaking faces. Experimental results showcase DiffTalker's superior performance in producing clear and geometrically accurate talking faces, all without the need for additional alignment between audio and image features., Comment: submmit to ICASSP 2024

Voice conversion is a method that allows for the transformation of speaking style while maintaining the integrity of linguistic information. There are many researchers using deep generative models for voice conversion tasks. Generative Adversarial Networks (GANs) can quickly generate high-quality samples, but the generated samples lack diversity. The samples generated by the Denoising Diffusion Probabilistic Models (DDPMs) are better than GANs in terms of mode coverage and sample diversity. But the DDPMs have high computational costs and the inference speed is slower than GANs. In order to make GANs and DDPMs more practical we proposes DiffGAN-VC, a variant of GANs and DDPMS, to achieve non-parallel many-to-many voice conversion (VC). We use large steps to achieve denoising, and also introduce a multimodal conditional GANs to model the denoising diffusion generative adversarial network. According to both objective and subjective evaluation experiments, DiffGAN-VC has been shown to achieve high voice quality on non-parallel data sets. Compared with the CycleGAN-VC method, DiffGAN-VC achieves speaker similarity, naturalness and higher sound quality., Comment: Accepted by 19th International Conference on Advanced Data Mining and Applications. (ADMA 2023)