Search

Text-to-audio (TTA), which generates audio signals from textual descriptions, has received huge attention in recent years. However, recent works focused on text to monaural audio only. As we know, spatial audio provides more immersive auditory experience than monaural audio, e.g. in virtual reality. To address this issue, we propose a text-to-spatial-audio (TTSA) generation framework named DualSpec.Specifically, it first trains variational autoencoders (VAEs) for extracting the latent acoustic representations from sound event audio. Then, given text that describes sound events and event directions, the proposed method uses the encoder of a pretrained large language model to transform the text into text features. Finally, it trains a diffusion model from the latent acoustic representations and text features for the spatial audio generation. In the inference stage, only the text description is needed to generate spatial audio. Particularly, to improve the synthesis quality and azimuth accuracy of the spatial sound events simultaneously, we propose to use two kinds of acoustic features. One is the Mel spectrograms which is good for improving the synthesis quality, and the other is the short-time Fourier transform spectrograms which is good at improving the azimuth accuracy. We provide a pipeline of constructing spatial audio dataset with text prompts, for the training of the VAEs and diffusion model. We also introduce new spatial-aware evaluation metrics to quantify the azimuth errors of the generated spatial audio recordings. Experimental results demonstrate that the proposed method can generate spatial audio with high directional and event consistency.

Text-to-audio (TTA) systems have recently demonstrated strong performance in synthesizing monaural audio from text. However, the task of generating binaural spatial audio from text, which provides a more immersive auditory experience by incorporating the sense of spatiality, have not been explored yet. In this work, we introduce text-guided binaural audio generation. As an early effort, we focus on the scenario where a monaural reference audio is given additionally. The core problem is to associate specific sound events with their directions, thereby creating binaural spatial audio. The challenge lies in the complexity of textual descriptions and the limited availability of single-source sound event datasets. To address this, we propose AudioSpa, an end-to-end model that applies large language models to process both acoustic and textual information. We employ fusion multi-head attention (FMHA) to integrate text tokens, which enhances the generation capability of the multimodal learning. Additionally, we propose a binaural source localization model to assess the quality of the generated audio. Finally, we design a data augmentation strategy to generate diverse datasets, which enables the model to spatialize sound events across various spatial positions. Experimental results demonstrate that our model is able to put sounds at the specified locations accurately. It achieves competitive performance in both localization accuracy and signal distortion. Our demonstrations are available at https://linfeng-feng.github.io/AudioSpa-demo.

As a natural multimodal content, audible video delivers an immersive sensory experience. Consequently, audio-video generation systems have substantial potential. However, existing diffusion-based studies mainly employ relatively independent modules for generating each modality, which lack exploration of shared-weight generative modules. This approach may under-use the intrinsic correlations between audio and visual modalities, potentially resulting in sub-optimal generation quality. To address this, we propose UniForm, a unified diffusion transformer designed to enhance cross-modal consistency. By concatenating auditory and visual information, UniForm learns to generate audio and video simultaneously within a unified latent space, facilitating the creation of high-quality and well-aligned audio-visual pairs. Extensive experiments demonstrate the superior performance of our method in joint audio-video generation, audio-guided video generation, and video-guided audio generation tasks. Our demos are available at https://uniform-t2av.github.io/., Comment: Our demos are available at https://uniform-t2av.github.io/

Target speech extraction (TSE) isolates the speech of a specific speaker from a multi-talker overlapped speech mixture. Most existing TSE models rely on discriminative methods, typically predicting a time-frequency spectrogram mask for the target speech. However, imperfections in these masks often result in over-/under-suppression of target/non-target speech, degrading perceptual quality. Generative methods, by contrast, re-synthesize target speech based on the mixture and target speaker cues, achieving superior perceptual quality. Nevertheless, these methods often overlook speech intelligibility, leading to alterations or loss of semantic content in the re-synthesized speech. Inspired by the Whisper model's success in target speaker ASR, we propose a generative TSE framework based on the pre-trained Whisper model to address the above issues. This framework integrates semantic modeling with flow-based acoustic modeling to achieve both high intelligibility and perceptual quality. Results from multiple benchmarks demonstrate that the proposed method outperforms existing generative and discriminative baselines. We present speech samples on our demo page., Comment: demo: https://aisaka0v0.github.io/GenerativeTSE_demo/

As a form of biometric authentication technology, the security of speaker verification systems is of utmost importance. However, SV systems are inherently vulnerable to various types of attacks that can compromise their accuracy and reliability. One such attack is voice conversion, which modifies a persons speech to sound like another person by altering various vocal characteristics. This poses a significant threat to SV systems. To address this challenge, the Source Speaker Tracing Challenge in IEEE SLT2024 aims to identify the source speaker information in manipulated speech signals. Specifically, SSTC focuses on source speaker verification against voice conversion to determine whether two converted speech samples originate from the same source speaker. In this study, we propose a speaker contrastive learning-based approach for source speaker tracing to learn the latent source speaker information in converted speech. To learn a more source-speaker-related representation, we employ speaker contrastive loss during the training of the embedding extractor. This speaker contrastive loss helps identify the true source speaker embedding among several distractor speaker embeddings, enabling the embedding extractor to learn the potentially possessing source speaker information present in the converted speech. Experiments demonstrate that our proposed speaker contrastive learning system achieves the lowest EER of 16.788% on the challenge test set, securing first place in the challenge., Comment: 7 pages, 2 figures, accepted by SLT

Recently, automatic speaker verification (ASV) based on deep learning is easily contaminated by adversarial attacks, which is a new type of attack that injects imperceptible perturbations to audio signals so as to make ASV produce wrong decisions. This poses a significant threat to the security and reliability of ASV systems. To address this issue, we propose a Diffusion-Based Adversarial Purification (DAP) method that enhances the robustness of ASV systems against such adversarial attacks. Our method leverages a conditional denoising diffusion probabilistic model to effectively purify the adversarial examples and mitigate the impact of perturbations. DAP first introduces controlled noise into adversarial examples, and then performs a reverse denoising process to reconstruct clean audio. Experimental results demonstrate the efficacy of the proposed DAP in enhancing the security of ASV and meanwhile minimizing the distortion of the purified audio signals., Comment: Accepted by IEEE Signal Processing Letters

The performance of speaker verification degrades significantly in adverse acoustic environments with strong reverberation and noise. To address this issue, this paper proposes a spatial-temporal graph convolutional network (GCN) method for the multi-channel speaker verification with ad-hoc microphone arrays. It includes a feature aggregation block and a channel selection block, both of which are built on graphs. The feature aggregation block fuses speaker features among different time and channels by a spatial-temporal GCN. The graph-based channel selection block discards the noisy channels that may contribute negatively to the system. The proposed method is flexible in incorporating various kinds of graphs and prior knowledge. We compared the proposed method with six representative methods in both real-world and simulated environments. Experimental results show that the proposed method achieves a relative equal error rate (EER) reduction of $\mathbf{15.39\%}$ lower than the strongest referenced method in the simulated datasets, and $\mathbf{17.70\%}$ lower than the latter in the real datasets. Moreover, its performance is robust across different signal-to-noise ratios and reverberation time.

The success of adversarial attacks to speaker recognition is mainly in white-box scenarios. When applying the adversarial voices that are generated by attacking white-box surrogate models to black-box victim models, i.e. \textit{transfer-based} black-box attacks, the transferability of the adversarial voices is not only far from satisfactory, but also lacks interpretable basis. To address these issues, in this paper, we propose a general framework, named spectral transformation attack based on modified discrete cosine transform (STA-MDCT), to improve the transferability of the adversarial voices to a black-box victim model. Specifically, we first apply MDCT to the input voice. Then, we slightly modify the energy of different frequency bands for capturing the salient regions of the adversarial noise in the time-frequency domain that are critical to a successful attack. Unlike existing approaches that operate voices in the time domain, the proposed framework operates voices in the time-frequency domain, which improves the interpretability, transferability, and imperceptibility of the attack. Moreover, it can be implemented with any gradient-based attackers. To utilize the advantage of model ensembling, we not only implement STA-MDCT with a single white-box surrogate model, but also with an ensemble of surrogate models. Finally, we visualize the saliency maps of adversarial voices by the class activation maps (CAM), which offers an interpretable basis to transfer-based attacks in speaker recognition for the first time. Extensive comparison results with five representative attackers show that the CAM visualization clearly explains the effectiveness of STA-MDCT, and the weaknesses of the comparison methods; the proposed method outperforms the comparison methods by a large margin.

Recently, the unified streaming and non-streaming two-pass (U2/U2++) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy and latency. In this paper, we present fast-U2++, an enhanced version of U2++ to further reduce partial latency. The core idea of fast-U2++ is to output partial results of the bottom layers in its encoder with a small chunk, while using a large chunk in the top layers of its encoder to compensate the performance degradation caused by the small chunk. Moreover, we use knowledge distillation method to reduce the token emission latency. We present extensive experiments on Aishell-1 dataset. Experiments and ablation studies show that compared to U2++, fast-U2++ reduces model latency from 320ms to 80ms, and achieves a character error rate (CER) of 5.06% with a streaming setup., Comment: 5 pages, 3 figures

Although the security of automatic speaker verification (ASV) is seriously threatened by recently emerged adversarial attacks, there have been some countermeasures to alleviate the threat. However, many defense approaches not only require the prior knowledge of the attackers but also possess weak interpretability. To address this issue, in this paper, we propose an attacker-independent and interpretable method, named learnable mask detector (LMD), to separate adversarial examples from the genuine ones. It utilizes score variation as an indicator to detect adversarial examples, where the score variation is the absolute discrepancy between the ASV scores of an original audio recording and its transformed audio synthesized from its masked complex spectrogram. A core component of the score variation detector is to generate the masked spectrogram by a neural network. The neural network needs only genuine examples for training, which makes it an attacker-independent approach. Its interpretability lies that the neural network is trained to minimize the score variation of the targeted ASV, and maximize the number of the masked spectrogram bins of the genuine training examples. Its foundation is based on the observation that, masking out the vast majority of the spectrogram bins with little speaker information will inevitably introduce a large score variation to the adversarial example, and a small score variation to the genuine example. Experimental results with 12 attackers and two representative ASV systems show that our proposed method outperforms five state-of-the-art baselines. The extensive experimental results can also be a benchmark for the detection-based ASV defenses., Comment: 13 pages, 9 figures

Adversarial attack approaches to speaker identification either need high computational cost or are not very effective, to our knowledge. To address this issue, in this paper, we propose a novel generation-network-based approach, called symmetric saliency-based encoder-decoder (SSED), to generate adversarial voice examples to speaker identification. It contains two novel components. First, it uses a novel saliency map decoder to learn the importance of speech samples to the decision of a targeted speaker identification system, so as to make the attacker focus on generating artificial noise to the important samples. It also proposes an angular loss function to push the speaker embedding far away from the source speaker. Our experimental results demonstrate that the proposed SSED yields the state-of-the-art performance, i.e. over 97% targeted attack success rate and a signal-to-noise level of over 39 dB on both the open-set and close-set speaker identification tasks, with a low computational cost.

Keyword spotting (KWS) enables speech-based user interaction and gradually becomes an indispensable component of smart devices. Recently, end-to-end (E2E) methods have become the most popular approach for on-device KWS tasks. However, there is still a gap between the research and deployment of E2E KWS methods. In this paper, we introduce WeKws, a production-quality, easy-to-build, and convenient-to-be-applied E2E KWS toolkit. WeKws contains the implementations of several state-of-the-art backbone networks, making it achieve highly competitive results on three publicly available datasets. To make WeKws a pure E2E toolkit, we utilize a refined max-pooling loss to make the model learn the ending position of the keyword by itself, which significantly simplifies the training pipeline and makes WeKws very efficient to be applied in real-world scenarios. The toolkit is publicly available at https://github.com/wenet-e2e/wekws.

While deep-learning-based speaker localization has shown advantages in challenging acoustic environments, it often yields only direction-of-arrival (DOA) cues rather than precise two-dimensional (2D) coordinates. To address this, we propose a novel deep-learning-based 2D speaker localization method leveraging ad-hoc microphone arrays, where an ad-hoc microphone array is composed of randomly distributed microphone nodes, each of which is equipped with a traditional array. Specifically, we first employ convolutional neural networks at each node to estimate speaker directions. Then, we integrate these DOA estimates using triangulation and clustering techniques to get 2D speaker locations. To further boost the estimation accuracy, we introduce a node selection algorithm that strategically filters the most reliable nodes. Extensive experiments on both simulated and real-world data demonstrate that our approach significantly outperforms conventional methods. The proposed node selection further refines performance. The real-world dataset in the experiment, named Libri-adhoc-node10 which is a newly recorded data described for the first time in this paper, is online available at https://github.com/Liu-sp/Libri-adhoc-nodes10.

Conventional sound source localization methods are mostly based on a single microphone array that consists of multiple microphones. They are usually formulated as the estimation of the direction of arrival problem. In this paper, we propose a deep-learning-based end-to-end sound source localization method with ad-hoc microphone arrays, where an ad-hoc microphone array is a set of randomly distributed microphone arrays that collaborate with each other. It can produce two-dimensional locations of speakers with only a single microphone per node. Specifically, we divide a targeted indoor space into multiple local areas. We encode each local area by a one-hot code, therefore, the node and speaker locations can be represented by the one-hot codes. Accordingly, the sound source localization problem is formulated as such a classification task of recognizing the one-hot code of the speaker given the one hot codes of the microphone nodes and their speech recordings. An end-to-end spatial-temporal deep model is designed for the classification problem. It utilizes a spatial-temporal attention architecture with a fusion layer inserted in the middle of the architecture, which is able to handle arbitrarily different numbers of microphone nodes during the model training and test. Experimental results show that the proposed method yields good performance in highly reverberant and noisy environments., Comment: 6 pages, 4 figures, coference

Speaker verification based on ad-hoc microphone arrays has the potential of reducing the error significantly in adverse acoustic environments. However, existing approaches extract utterance-level speaker embeddings from each channel of an ad-hoc microphone array, which does not consider fully the spatial-temporal information across the devices. In this paper, we propose to aggregate the multichannel signals of the ad-hoc microphone array at the frame-level by exploring the cross-channel information deeply with two attention mechanisms. The first one is a self-attention method. It consists of a cross-frame self-attention layer and a cross-channel self-attention layer successively, both working at the frame level. The second one learns the cross-frame and cross-channel information via two graph attention layers. Experimental results demonstrate that the proposed methods reach the state-of-the-art performance. Moreover, the graph-attention method is better than the self-attention method in most cases., Comment: 5 pages, 3 figures

Transformer-based end-to-end speech recognition models have received considerable attention in recent years due to their high training speed and ability to model a long-range global context. Position embedding in the transformer architecture is indispensable because it provides supervision for dependency modeling between elements at different positions in the input sequence. To make use of the time order of the input sequence, many works inject some information about the relative or absolute position of the element into the input sequence. In this work, we investigate various position embedding methods in the convolution-augmented transformer (conformer) and adopt a novel implementation named rotary position embedding (RoPE). RoPE encodes absolute positional information into the input sequence by a rotation matrix, and then naturally incorporates explicit relative position information into a self-attention module. To evaluate the effectiveness of the RoPE method, we conducted experiments on AISHELL-1 and LibriSpeech corpora. Results show that the conformer enhanced with RoPE achieves superior performance in the speech recognition task. Specifically, our model achieves a relative word error rate reduction of 8.70% and 7.27% over the conformer on test-clean and test-other sets of the LibriSpeech corpus respectively., Comment: 5 pages, 3 figures

Deep neural networks provide effective solutions to small-footprint keyword spotting (KWS). However, if training data is limited, it remains challenging to achieve robust and highly accurate KWS in real-world scenarios where unseen sounds that are out of the training data are frequently encountered. Most conventional methods aim to maximize the classification accuracy on the training set, without taking the unseen sounds into account. To enhance the robustness of the deep neural networks based KWS, in this paper, we introduce a new loss function, named the maximization of the area under the receiver-operating-characteristic curve (AUC). The proposed method not only maximizes the classification accuracy of keywords on the closed training set, but also maximizes the AUC score for optimizing the performance of non-keyword segments detection. Experimental results on the Google Speech Commands dataset v1 and v2 show that our method achieves new state-of-the-art performance in terms of most evaluation metrics., Comment: submitted to ASRU2021

Recently, ad-hoc microphone array has been widely studied. Unlike traditional microphone array settings, the spatial arrangement and number of microphones of ad-hoc microphone arrays are not known in advance, which hinders the adaptation of traditional speaker verification technologies to ad-hoc microphone arrays. To overcome this weakness, in this paper, we propose attention-based multi-channel speaker verification with ad-hoc microphone arrays. Specifically, we add an inter-channel processing layer and a global fusion layer after the pooling layer of a single-channel speaker verification system. The inter-channel processing layer applies a so-called residual self-attention along the channel dimension for allocating weights to different microphones. The global fusion layer integrates all channels in a way that is independent to the number of the input channels. We further replace the softmax operator in the residual self-attention with sparsemax, which forces the channel weights of very noisy channels to zero. Experimental results with ad-hoc microphone arrays of over 30 channels demonstrate the effectiveness of the proposed methods. For example, the multi-channel speaker verification with sparsemax achieves an equal error rate (EER) of over 20% lower than oracle one-best system on semi-real data sets, and over 30% lower on simulation data sets, in test scenarios with both matched and mismatched channel numbers., Comment: Submitted to APSIPA ASC 2021

Recently, conformer-based end-to-end automatic speech recognition, which outperforms recurrent neural network based ones, has received much attention. Although the parallel computing of conformer is more efficient than recurrent neural networks, the computational complexity of its dot-product self-attention is quadratic with respect to the length of the input feature. To reduce the computational complexity of the self-attention layer, we propose multi-head linear self-attention for the self-attention layer, which reduces its computational complexity to linear order. In addition, we propose to factorize the feed forward module of the conformer by low-rank matrix factorization, which successfully reduces the number of the parameters by approximate 50% with little performance loss. The proposed model, named linear attention based conformer (LAC), can be trained and inferenced jointly with the connectionist temporal classification objective, which further improves the performance of LAC. To evaluate the effectiveness of LAC, we conduct experiments on the AISHELL-1 and LibriSpeech corpora. Results show that the proposed LAC achieves better performance than 7 recently proposed speech recognition models, and is competitive with the state-of-the-art conformer. Meanwhile, the proposed LAC has a number of parameters of only 50% over the conformer with faster training speed than the latter., Comment: submitted to APSIPA ASC 2021

Self-attention (SA), which encodes vector sequences according to their pairwise similarity, is widely used in speech recognition due to its strong context modeling ability. However, when applied to long sequence data, its accuracy is reduced. This is caused by the fact that its weighted average operator may lead to the dispersion of the attention distribution, which results in the relationship between adjacent signals ignored. To address this issue, in this paper, we introduce relative-position-awareness self-attention (RPSA). It not only maintains the global-range dependency modeling ability of self-attention, but also improves the localness modeling ability. Because the local window length of the original RPSA is fixed and sensitive to different test data, here we propose Gaussian-based self-attention (GSA) whose window length is learnable and adaptive to the test data automatically. We further generalize GSA to a new residual Gaussian self-attention (resGSA) for the performance improvement. We apply RPSA, GSA, and resGSA to Transformer-based speech recognition respectively. Experimental results on the AISHELL-1 Mandarin speech recognition corpus demonstrate the effectiveness of the proposed methods. For example, the resGSA-Transformer achieves a character error rate (CER) of 5.86% on the test set, which is relative 7.8% lower than that of the SA-Transformer. Although the performance of the proposed resGSA-Transformer is only slightly better than that of the RPSA-Transformer, it does not have to tune the window length manually., Comment: There is an error in the description of section 3.2.1

Recently, speech recognition with ad-hoc microphone arrays has received much attention. It is known that channel selection is an important problem of ad-hoc microphone arrays, however, this topic seems far from explored in speech recognition yet, particularly with a large-scale ad-hoc microphone array. To address this problem, we propose a Scaling Sparsemax algorithm for the channel selection problem of the speech recognition with large-scale ad-hoc microphone arrays. Specifically, we first replace the conventional Softmax operator in the stream attention mechanism of a multichannel end-to-end speech recognition system with Sparsemax, which conducts channel selection by forcing the channel weights of noisy channels to zero. Because Sparsemax punishes the weights of many channels to zero harshly, we propose Scaling Sparsemax which punishes the channels mildly by setting the weights of very noisy channels to zero only. Experimental results with ad-hoc microphone arrays of over 30 channels under the conformer speech recognition architecture show that the proposed Scaling Sparsemax yields a word error rate of over 30% lower than Softmax on simulation data sets, and over 20% lower on semi-real data sets, in test scenarios with both matched and mismatched channel numbers.

Multichannel blind audio source separation aims to recover the latent sources from their multichannel mixtures without supervised information. One state-of-the-art blind audio source separation method, named independent low-rank matrix analysis (ILRMA), unifies independent vector analysis (IVA) and nonnegative matrix factorization (NMF). However, the spectra matrix produced from NMF may not find a compact spectral basis. It may not guarantee the identifiability of each source as well. To address this problem, here we propose to enhance the identifiability of the source model by a minimum-volume prior distribution. We further regularize a multichannel NMF (MNMF) and ILRMA respectively with the minimum-volume regularizer. The proposed methods maximize the posterior distribution of the separated sources, which ensures the stability of the convergence. Experimental results demonstrate the effectiveness of the proposed methods compared with auxiliary independent vector analysis, MNMF, ILRMA and its extensions.

Recently, the research on ad-hoc microphone arrays with deep learning has drawn much attention, especially in speech enhancement and separation. Because an ad-hoc microphone array may cover such a large area that multiple speakers may locate far apart and talk independently, target-dependent speech separation, which aims to extract a target speaker from a mixed speech, is important for extracting and tracing a specific speaker in the ad-hoc array. However, this technique has not been explored yet. In this paper, we propose deep ad-hoc beamforming based on speaker extraction, which is to our knowledge the first work for target-dependent speech separation based on ad-hoc microphone arrays and deep learning. The algorithm contains three components. First, we propose a supervised channel selection framework based on speaker extraction, where the estimated utterance-level SNRs of the target speech are used as the basis for the channel selection. Second, we apply the selected channels to a deep learning based MVDR algorithm, where a single-channel speaker extraction algorithm is applied to each selected channel for estimating the mask of the target speech. We conducted an extensive experiment on a WSJ0-adhoc corpus. Experimental results demonstrate the effectiveness of the proposed method.

The design of acoustic features is important for speech separation. It can be roughly categorized into three classes: handcrafted, parameterized, and learnable features. Among them, learnable features, which are trained with separation networks jointly in an end-to-end fashion, become a new trend of modern speech separation research, e.g. convolutional time domain audio separation network (Conv-Tasnet), while handcrafted and parameterized features are also shown competitive in very recent studies. However, a systematic comparison across the three kinds of acoustic features has not been conducted yet. In this paper, we compare them in the framework of Conv-Tasnet by setting its encoder and decoder with different acoustic features. We also generalize the handcrafted multi-phase gammatone filterbank (MPGTF) to a new parameterized multi-phase gammatone filterbank (ParaMPGTF). Experimental results on the WSJ0-2mix corpus show that (i) if the decoder is learnable, then setting the encoder to STFT, MPGTF, ParaMPGTF, and learnable features lead to similar performance; and (ii) when the pseudo-inverse transforms of STFT, MPGTF, and ParaMPGTF are used as the decoders, the proposed ParaMPGTF performs better than the other two handcrafted features.

Recently, several studies reported that dot-product selfattention (SA) may not be indispensable to the state-of-theart Transformer models. Motivated by the fact that dense synthesizer attention (DSA), which dispenses with dot products and pairwise interactions, achieved competitive results in many language processing tasks, in this paper, we first propose a DSA-based speech recognition, as an alternative to SA. To reduce the computational complexity and improve the performance, we further propose local DSA (LDSA) to restrict the attention scope of DSA to a local range around the current central frame for speech recognition. Finally, we combine LDSA with SA to extract the local and global information simultaneously. Experimental results on the Ai-shell1 Mandarine speech recognition corpus show that the proposed LDSA-Transformer achieves a character error rate (CER) of 6.49%, which is slightly better than that of the SA-Transformer. Meanwhile, the LDSA-Transformer requires less computation than the SATransformer. The proposed combination method not only achieves a CER of 6.18%, which significantly outperforms the SA-Transformer, but also has roughly the same number of parameters and computational complexity as the latter. The implementation of the multi-head LDSA is available at https://github.com/mlxu995/multihead-LDSA., Comment: 5 pages, 3 figures

Robust voice activity detection (VAD) is a challenging task in low signal-to-noise (SNR) environments. Recent studies show that speech enhancement is helpful to VAD, but the performance improvement is limited. To address this issue, here we propose a speech enhancement aided end-to-end multi-task model for VAD. The model has two decoders, one for speech enhancement and the other for VAD. The two decoders share the same encoder and speech separation network. Unlike the direct thought that takes two separated objectives for VAD and speech enhancement respectively, here we propose a new joint optimization objective -- VAD-masked scale-invariant source-to-distortion ratio (mSI-SDR). mSI-SDR uses VAD information to mask the output of the speech enhancement decoder in the training process. It makes the VAD and speech enhancement tasks jointly optimized not only at the shared encoder and separation network, but also at the objective level. It also satisfies real-time working requirement theoretically. Experimental results show that the multi-task method significantly outperforms its single-task VAD counterpart. Moreover, mSI-SDR outperforms SI-SDR in the same multi-task setting., Comment: Accepted by ICASSP2021

One difficult problem of keyword spotting is how to miniaturize its memory footprint while maintain a high precision. Although convolutional neural networks have shown to be effective to the small-footprint keyword spotting problem, they still need hundreds of thousands of parameters to achieve good performance. In this paper, we propose an efficient model based on depthwise separable convolution layers and squeeze-and-excitation blocks. Specifically, we replace the standard convolution by the depthwise separable convolution, which reduces the number of the parameters of the standard convolution without significant performance degradation. We further improve the performance of the depthwise separable convolution by reweighting the output feature maps of the first convolution layer with a so-called squeeze-and-excitation block. We compared the proposed method with five representative models on two experimental settings of the Google Speech Commands dataset. Experimental results show that the proposed method achieves the state-of-the-art performance. For example, it achieves a classification error rate of 3.29% with a number of parameters of 72K in the first experiment, which significantly outperforms the comparison methods given a similar model size. It achieves an error rate of 3.97% with a number of parameters of 10K, which is also slightly better than the state-of-the-art comparison method given a similar model size.

Deep embedding based text-independent speaker verification has demonstrated superior performance to traditional methods in many challenging scenarios. Its loss functions can be generally categorized into two classes, i.e., verification and identification. The verification loss functions match the pipeline of speaker verification, but their implementations are difficult. Thus, most state-of-the-art deep embedding methods use the identification loss functions with softmax output units or their variants. In this paper, we propose a verification loss function, named the maximization of partial area under the Receiver-operating-characteristic (ROC) curve (pAUC), for deep embedding based text-independent speaker verification. We also propose a class-center based training trial construction method to improve the training efficiency, which is critical for the proposed loss function to be comparable to the identification loss in performance. Experiments on the Speaker in the Wild (SITW) and NIST SRE 2016 datasets show that the proposed pAUC loss function is highly competitive with the state-of-the-art identification loss functions.

Recently, deep clustering (DPCL) based speaker-independent speech separation has drawn much attention, since it needs little speaker prior information. However, it still has much room of improvement, particularly in reverberant environments. If the training and test environments mismatch which is a common case, the embedding vectors produced by DPCL may contain much noise and many small variations. To deal with the problem, we propose a variant of DPCL, named DPCL++, by applying a recent unsupervised deep learning method---multilayer bootstrap networks(MBN)---to further reduce the noise and small variations of the embedding vectors in an unsupervised way in the test stage, which fascinates k-means to produce a good result. MBN builds a gradually narrowed network from bottom-up via a stack of k-centroids clustering ensembles, where the k-centroids clusterings are trained independently by random sampling and one-nearest-neighbor optimization. To further improve the robustness of DPCL++ in reverberant environments, we take spatial features as part of its input. Experimental results demonstrate the effectiveness of the proposed method.

Far-field speech processing is an important and challenging problem. In this paper, we propose \textit{deep ad-hoc beamforming}, a deep-learning-based multichannel speech enhancement framework based on ad-hoc microphone arrays, to address the problem. It contains three novel components. First, it combines \textit{ad-hoc microphone arrays} with deep-learning-based multichannel speech enhancement, which reduces the probability of the occurrence of far-field acoustic environments significantly. Second, it groups the microphones around the speech source to a local microphone array by a supervised channel selection framework based on deep neural networks. Third, it develops a simple time synchronization framework to synchronize the channels that have different time delay. Besides the above novelties and advantages, the proposed model is also trained in a single-channel fashion, so that it can easily employ new development of speech processing techniques. Its test stage is also flexible in incorporating any number of microphones without retraining or modifying the framework. We have developed many implementations of the proposed framework and conducted an extensive experiment in scenarios where the locations of the speech sources are far-field, random, and blind to the microphones. Results on speech enhancement tasks show that our method outperforms its counterpart that works with linear microphone arrays by a considerable margin in both diffuse noise reverberant environments and point source noise reverberant environments. We have also tested the framework with different handcrafted features. Results show that although designing good features lead to high performance, they do not affect the conclusion on the effectiveness of the proposed framework., Comment: Accepted by Computer Speech and Language

This paper presents a linear regression based back-end for speaker verification. Linear regression is a simple linear model that minimizes the mean squared estimation error between the target and its estimate with a closed form solution, where the target is defined as the ground-truth indicator vectors of utterances. We use the linear regression model to learn speaker models from a front-end, and verify the similarity of two speaker models by a cosine similarity scoring classifier. To evaluate the effectiveness of the linear regression model, we construct three speaker verification systems that use the Gaussian mixture model and identity-vector (GMM/i-vector) front-end, deep neural network and i-vector (DNN/i-vector) front-end, and deep vector (d-vector) front-end as their front-ends, respectively. Our empirical comparison results on the NIST speaker recognition evaluation data sets show that the proposed method outperforms within-class covariance normalization, linear discriminant analysis, and probabilistic linear discriminant analysis, given any of the three front-ends.

In this paper, we propose a universal background model, named universal background sparse coding (UBSC), for speaker verification. The proposed method trains an ensemble of clusterings by data resampling, and produces sparse codes from the clusterings by one-nearest-neighbor optimization plus binarization. The main advantage of UBSC is that it does not suffer from local minima and does not make Gaussian assumptions on data distributions. We evaluated UBSC on a clean speech corpus---TIMIT. We used the cosine similarity and inner product similarity as the scoring methods of a trial. Experimental results show that UBSC is comparable to Gaussian mixture model.

We apply multilayer bootstrap network (MBN), a recent proposed unsupervised learning method, to unsupervised speaker recognition. The proposed method first extracts supervectors from an unsupervised universal background model, then reduces the dimension of the high-dimensional supervectors by multilayer bootstrap network, and finally conducts unsupervised speaker recognition by clustering the low-dimensional data. The comparison results with 2 unsupervised and 1 supervised speaker recognition techniques demonstrate the effectiveness and robustness of the proposed method.

Recently, the deep-belief-networks (DBN) based voice activity detection (VAD) has been proposed. It is powerful in fusing the advantages of multiple features, and achieves the state-of-the-art performance. However, the deep layers of the DBN-based VAD do not show an apparent superiority to the shallower layers. In this paper, we propose a denoising-deep-neural-network (DDNN) based VAD to address the aforementioned problem. Specifically, we pre-train a deep neural network in a special unsupervised denoising greedy layer-wise mode, and then fine-tune the whole network in a supervised way by the common back-propagation algorithm. In the pre-training phase, we take the noisy speech signals as the visible layer and try to extract a new feature that minimizes the reconstruction cross-entropy loss between the noisy speech signals and its corresponding clean speech signals. Experimental results show that the proposed DDNN-based VAD not only outperforms the DBN-based VAD but also shows an apparent performance improvement of the deep layers over shallower layers., Comment: This paper has been accepted by IEEE ICASSP-2013, and will be published online after May, 2013