Search

Language mismatch is among the most common and challenging domain mismatches in deploying speaker verification (SV) systems. Adversarial reprogramming has shown promising results in cross-language adaptation for SV. The reprogramming is implemented by padding learnable parameters on the two sides of input speech signals. In this paper, we investigate the relationship between the number of padded parameters and the performance of the reprogrammed models. Sufficient experiments are conducted with different scales of SV models and datasets. The results demonstrate that reprogramming consistently improves the performance of cross-language SV, while the improvement is saturated or even degraded when using larger padding lengths. The performance is mainly determined by the capacity of the original SV models instead of the number of padded parameters. The SV models with larger scales have higher upper bounds in performance and can endure longer padding without performance degradation., Comment: Accepted by ISCSLP 2024

Psychotherapy or counseling is typically conducted through spoken conversation between a therapist and a client. Analyzing the speech characteristics of psychotherapeutic interactions can help understand the factors associated with effective psychotherapy. This paper introduces CUEMPATHY, a large-scale speech dataset collected from actual counseling sessions. The dataset consists of 156 counseling sessions involving 39 therapist-client dyads. The process of speech data collection, subjective ratings (one observer and two client ratings), and transcription are described. An automatic speech and text processing system is developed to locate the time stamps of speaker turns in each session. Examining the relationships among the three subjective ratings suggests that observer and client ratings have no significant correlation, while the client-rated measures are significantly correlated. The intensity similarity between the therapist and the client, measured by the averaged absolute difference of speaker-turn-level intensities, is associated with the psychotherapy outcomes. Recent studies on the acoustic and linguistic characteristics of the CUEMPATHY are introduced., Comment: Accepted by ISCSLP 2022

This paper presents a user-driven approach for synthesizing specific target voices based on user feedback rather than reference recordings, which is particularly beneficial for speech-impaired individuals who want to recreate their lost voices but lack prior recordings. Our method leverages the neural analysis and synthesis framework to construct a latent speaker embedding space. Within this latent space, a human-in-the-loop search algorithm guides the voice generation process. Users participate in a series of straightforward listening-and-comparison tasks, providing feedback that iteratively refines the synthesized voice to match their desired target. Both computer simulations and real-world user studies demonstrate that the proposed approach can effectively approximate target voices. Moreover, by analyzing the mel-spectrogram generator's Jacobians, we identify a set of meaningful voice editing directions within the latent space. These directions enable users to further fine-tune specific attributes of the generated voice, including the pitch level, pitch range, volume, vocal tension, nasality, and tone color. Audio samples are available at https://myspeechprojects.github.io/voicedesign/., Comment: This work has been submitted to the IEEE for possible publication

Representing speech as discretized units has numerous benefits in supporting downstream spoken language processing tasks. However, the approach has been less explored in speech synthesis of tonal languages like Mandarin Chinese. Our preliminary experiments on Chinese speech synthesis reveal the issue of "tone shift", where a synthesized speech utterance contains correct base syllables but incorrect tones. To address the issue, we propose the ToneUnit framework, which leverages annotated data with tone labels as CTC supervision to learn tone-aware discrete speech units for Mandarin Chinese speech. Our findings indicate that the discrete units acquired through the TonUnit resolve the "tone shift" issue in synthesized Chinese speech and yield favorable results in English synthesis. Moreover, the experimental results suggest that finite scalar quantization enhances the effectiveness of ToneUnit. Notably, ToneUnit can work effectively even with minimal annotated data.

Covering all languages with a multilingual speech recognition model (MASR) is very difficult. Performing language extension on top of an existing MASR is a desirable choice. In this study, the MASR continual learning problem is probabilistically decomposed into language identity prediction (LP) and cross-lingual adaptation (XLA) sub-problems. Based on this, we propose an architecture-based framework for language extension that can fundamentally solve catastrophic forgetting, debudded as PELE. PELE is designed to be parameter-efficient, incrementally incorporating an add-on module to adapt to a new language. Specifically, different parameter-efficient fine-tuning (PEFT) modules and their variants are explored as potential candidates to perform XLA. Experiments are carried out on 5 new languages with a wide range of low-resourced data sizes. The best-performing PEFT candidate can achieve satisfactory performance across all languages and demonstrates superiority in three of five languages over the continual joint learning setting. Notably, PEFT methods focusing on weight parameters or input features are revealed to be limited in performance, showing significantly inferior extension capabilities compared to inserting a lightweight module in between layers such as an Adapter., Comment: Accepted by Interspeech 2024

Toward high-performance multilingual automatic speech recognition (ASR), various types of linguistic information and model design have demonstrated their effectiveness independently. They include language identity (LID), phoneme information, language-specific processing modules, and cross-lingual self-supervised speech representation. It is expected that leveraging their benefits synergistically in a unified solution would further improve the overall system performance. This paper presents a novel design of a hierarchical information path, named LUPET, which sequentially encodes, from the shallow layers to deep layers, multiple aspects of linguistic and acoustic information at diverse granularity scales. The path starts from LID prediction, followed by acoustic unit discovery, phoneme sharing, and finally token recognition routed by a mixture-of-expert. ASR experiments are carried out on 10 languages in the Common Voice corpus. The results demonstrate the superior performance of LUPET as compared to the baseline systems. Most importantly, LUPET effectively mitigates the issue of performance compromise of high-resource languages with low-resource ones in the multilingual setting., Comment: Accepted by Interspeech 2024

This research is about the creation of personalized synthetic voices for head and neck cancer survivors. It is focused particularly on tongue cancer patients whose speech might exhibit severe articulation impairment. Our goal is to restore normal articulation in the synthesized speech, while maximally preserving the target speaker's individuality in terms of both the voice timbre and speaking style. This is formulated as a task of learning from noisy labels. We propose to augment the commonly used speech reconstruction loss with two additional terms. The first term constitutes a regularization loss that mitigates the impact of distorted articulation in the training speech. The second term is a consistency loss that encourages correct articulation in the generated speech. These additional loss terms are obtained from frame-level articulation scores of original and generated speech, which are derived using a separately trained phone classifier. Experimental results on a real case of tongue cancer patient confirm that the synthetic voice achieves comparable articulation quality to unimpaired natural speech, while effectively maintaining the target speaker's individuality. Audio samples are available at https://myspeechproject.github.io/ArticulationRepair/., Comment: Accepted to ICASSP 2024

Counseling is carried out as spoken conversation between a therapist and a client. The empathy level expressed by the therapist is considered an important index of the quality of counseling and often assessed by an observer or the client. This research investigates the entrainment of speech prosody in relation to subjectively rated empathy. Experimental results show that the entrainment of intensity is more influential to empathy observation than that of pitch or speech rate in client-therapist interaction. The observer and the client have different perceptions of therapist empathy with the same entrained phenomena in pitch and intensity. The client's intention to make adjustment on pitch variation and intensity of speech is considered an indicator of the client's perception of counseling quality., Comment: Accepted by INTERSPEECH 2023

Counseling is usually conducted through spoken conversation between a therapist and a client. The empathy level of therapist is a key indicator of outcomes. Presuming that therapist's empathy expression is shaped by their past behavior and their perception of the client's behavior, we propose a model to estimate the therapist empathy by considering both intrapersonal and interpersonal influences. These dynamic influences are captured by applying an attention mechanism to the therapist turn and the historical turns of both therapist and client. Our findings suggest that the integration of dynamic influences enhances empathy level estimation. The influence-derived embedding should constitute a minor portion of the target turn representation for optimal empathy estimation. The client's turns (interpersonal influence) slightly surpass the therapist's own turns (intrapersonal influence) in empathy estimation effectiveness. It is noted that concentrating exclusively on recent historical turns can significantly impact the estimation of therapist empathy., Comment: Accepted by ICASSP 2024

The development of deep neural networks (DNN) has significantly enhanced the performance of speaker verification (SV) systems in recent years. However, a critical issue that persists when applying DNN-based SV systems in practical applications is domain mismatch. To mitigate the performance degradation caused by the mismatch, domain adaptation becomes necessary. This paper introduces an approach to adapt DNN-based SV models by manipulating the learnable model inputs, inspired by the concept of adversarial reprogramming. The pre-trained SV model remains fixed and functions solely in the forward process, resembling a black-box model. A lightweight network is utilized to estimate the gradients for the learnable parameters at the input, which bypasses the gradient backpropagation through the black-box model. The reprogrammed output is processed by a two-layer backend learning module as the final adapted speaker embedding. The number of parameters involved in the gradient calculation is small in our design. With few additional parameters, the proposed method achieves both memory and parameter efficiency. The experiments are conducted in language mismatch scenarios. Using much less computation cost, the proposed method obtains close or superior performance to the fully finetuned models in our experiments, which demonstrates its effectiveness.

Transformer-based speech recognition (ASR) model with deep layers exhibited significant performance improvement. However, the model is inefficient for deployment on resource-constrained devices. Layer pruning (LP) is a commonly used compression method to remove redundant layers. Previous studies on LP usually identify the redundant layers according to a task-specific evaluation metric. They are time-consuming for models with a large number of layers, even in a greedy search manner. To address this problem, we propose CoMFLP, a fast search LP algorithm based on correlation measure. The correlation between layers is computed to generate a correlation matrix, which identifies the redundancy among layers. The search process is carried out in two steps: (1) coarse search: to determine top $K$ candidates by pruning the most redundant layers based on the correlation matrix; (2) fine search: to select the best pruning proposal among $K$ candidates using a task-specific evaluation metric. Experiments on an ASR task show that the pruning proposal determined by CoMFLP outperforms existing LP methods while only requiring constant time complexity. The code is publicly available at https://github.com/louislau1129/CoMFLP., Comment: Accepted by Interspeech 2023

Whisper is a powerful automatic speech recognition (ASR) model. Nevertheless, its zero-shot performance on low-resource speech requires further improvement. Child speech, as a representative type of low-resource speech, is leveraged for adaptation. Recently, parameter-efficient fine-tuning (PEFT) in NLP was shown to be comparable and even better than full fine-tuning, while only needing to tune a small set of trainable parameters. However, current PEFT methods have not been well examined for their effectiveness on Whisper. In this paper, only parameter composition types of PEFT approaches such as LoRA and Bitfit are investigated as they do not bring extra inference costs. Different popular PEFT methods are examined. Particularly, we compare LoRA and AdaLoRA and figure out the learnable rank coefficient is a good design. Inspired by the sparse rank distribution allocated by AdaLoRA, a novel PEFT approach Sparsely Shared LoRA (S2-LoRA) is proposed. The two low-rank decomposed matrices are globally shared. Each weight matrix only has to maintain its specific rank coefficients that are constrained to be sparse. Experiments on low-resource Chinese child speech show that with much fewer trainable parameters, S2-LoRA can achieve comparable in-domain adaptation performance to AdaLoRA and exhibit better generalization ability on out-of-domain data. In addition, the rank distribution automatically learned by S2-LoRA is found to have similar patterns to AdaLoRA's allocation., Comment: Accepted by ICASSP 2024

While state-of-the-art Text-to-Speech systems can generate natural speech of very high quality at sentence level, they still meet great challenges in speech generation for paragraph / long-form reading. Such deficiencies are due to i) ignorance of cross-sentence contextual information, and ii) high computation and memory cost for long-form synthesis. To address these issues, this work develops a lightweight yet effective TTS system, ContextSpeech. Specifically, we first design a memory-cached recurrence mechanism to incorporate global text and speech context into sentence encoding. Then we construct hierarchically-structured textual semantics to broaden the scope for global context enhancement. Additionally, we integrate linearized self-attention to improve model efficiency. Experiments show that ContextSpeech significantly improves the voice quality and prosody expressiveness in paragraph reading with competitive model efficiency. Audio samples are available at: https://contextspeech.github.io/demo/, Comment: 5 pages, 4 figures, Proceedings of Interspeech 2023

This paper is about developing personalized speech synthesis systems with recordings of mildly impaired speech. In particular, we consider consonant and vowel alterations resulted from partial glossectomy, the surgical removal of part of the tongue. The aim is to restore articulation in the synthesized speech and maximally preserve the target speaker's individuality. We propose to tackle the problem with guided diffusion models. Specifically, a diffusion-based speech synthesis model is trained on original recordings, to capture and preserve the target speaker's original articulation style. When using the model for inference, a separately trained phone classifier will guide the synthesis process towards proper articulation. Objective and subjective evaluation results show that the proposed method substantially improves articulation in the synthesized speech over original recordings, and preserves more of the target speaker's individuality than a voice conversion baseline., Comment: submitted to INTERSPEECH 2023

Counseling is an activity of conversational speaking between a therapist and a client. Therapist empathy is an essential indicator of counseling quality and assessed subjectively by considering the entire conversation. This paper proposes to encode long counseling conversation using a hierarchical attention network. Conversations with extreme values of empathy rating are used to train a Siamese network based encoder with contrastive loss. Two-level attention mechanisms are applied to learn the importance weights of individual speaker turns and groups of turns in the conversation. Experimental results show that the use of contrastive loss is effective in encouraging the conversation encoder to learn discriminative embeddings that are related to therapist empathy. The distances between conversation embeddings positively correlate with the differences in the respective empathy scores. The learned conversation embeddings can be used to predict the subjective rating of therapist empathy., Comment: Accepted by INTERSPEECH 2024

Creating synthetic voices with found data is challenging, as real-world recordings often contain various types of audio degradation. One way to address this problem is to pre-enhance the speech with an enhancement model and then use the enhanced data for text-to-speech (TTS) model training. This paper investigates the use of conditional diffusion models for generalized speech enhancement, which aims at addressing multiple types of audio degradation simultaneously. The enhancement is performed on the log Mel-spectrogram domain to align with the TTS training objective. Text information is introduced as an additional condition to improve the model robustness. Experiments on real-world recordings demonstrate that the synthetic voice built on data enhanced by the proposed model produces higher-quality synthetic speech, compared to those trained on data enhanced by strong baselines. Code and pre-trained parameters of the proposed enhancement model are available at \url{https://github.com/dmse4tts/DMSE4TTS}, Comment: Accepted to ASRU 2023

Recent studies on pronunciation scoring have explored the effect of introducing phone embeddings as reference pronunciation, but mostly in an implicit manner, i.e., addition or concatenation of reference phone embedding and actual pronunciation of the target phone as the phone-level pronunciation quality representation. In this paper, we propose to use linguistic-acoustic similarity to explicitly measure the deviation of non-native production from its native reference for pronunciation assessment. Specifically, the deviation is first estimated by the cosine similarity between reference phone embedding and corresponding acoustic embedding. Next, a phone-level Goodness of pronunciation (GOP) pre-training stage is introduced to guide this similarity-based learning for better initialization of the aforementioned two embeddings. Finally, a transformer-based hierarchical pronunciation scorer is used to map a sequence of phone embeddings, acoustic embeddings along with their similarity measures to predict the final utterance-level score. Experimental results on the non-native databases suggest that the proposed system significantly outperforms the baselines, where the acoustic and phone embeddings are simply added or concatenated. A further examination shows that the phone embeddings learned in the proposed approach are able to capture linguistic-acoustic attributes of native pronunciation as reference., Comment: Accepted by ICASSP 2023

A typical fluency scoring system generally relies on an automatic speech recognition (ASR) system to obtain time stamps in input speech for either the subsequent calculation of fluency-related features or directly modeling speech fluency with an end-to-end approach. This paper describes a novel ASR-free approach for automatic fluency assessment using self-supervised learning (SSL). Specifically, wav2vec2.0 is used to extract frame-level speech features, followed by K-means clustering to assign a pseudo label (cluster index) to each frame. A BLSTM-based model is trained to predict an utterance-level fluency score from frame-level SSL features and the corresponding cluster indexes. Neither speech transcription nor time stamp information is required in the proposed system. It is ASR-free and can potentially avoid the ASR errors effect in practice. Experimental results carried out on non-native English databases show that the proposed approach significantly improves the performance in the "open response" scenario as compared to previous methods and matches the recently reported performance in the "read aloud" scenario., Comment: Accepted by ICASSP 2023

Very deep models for speaker recognition (SR) have demonstrated remarkable performance improvement in recent research. However, it is impractical to deploy these models for on-device applications with constrained computational resources. On the other hand, light-weight models are highly desired in practice despite their sub-optimal performance. This research aims to improve light-weight SR models through large-scale label-free knowledge distillation (KD). Existing KD approaches for SR typically require speaker labels to learn task-specific knowledge, due to the inefficiency of conventional loss for distillation. To address the inefficiency problem and achieve label-free KD, we propose to employ the contrastive loss from self-supervised learning for distillation. Extensive experiments are conducted on a collection of public speech datasets from diverse sources. Results on light-weight SR models show that the proposed approach of label-free KD with contrastive loss consistently outperforms both conventional distillation methods and self-supervised learning methods by a significant margin.

Probabilistic linear discriminant analysis (PLDA) is commonly used in speaker verification systems to score the similarity of speaker embeddings. Recent studies improved the performance of PLDA in domain-matched conditions by diagonalizing its covariance. We suspect such brutal pruning approach could eliminate its capacity in modeling dimension correlation of speaker embeddings, leading to inadequate performance with domain adaptation. This paper explores two alternative covariance regularization approaches, namely, interpolated PLDA and sparse PLDA, to tackle the problem. The interpolated PLDA incorporates the prior knowledge from cosine scoring to interpolate the covariance of PLDA. The sparse PLDA introduces a sparsity penalty to update the covariance. Experimental results demonstrate that both approaches outperform diagonal regularization noticeably with domain adaptation. In addition, in-domain data can be significantly reduced when training sparse PLDA for domain adaptation.

DNN-based speaker verification (SV) models demonstrate significant performance at relatively high computation costs. Model compression can be applied to reduce the model size for lower resource consumption. The present study exploits weight quantization to compress two widely-used SV models, namely ECAPA-TDNN and ResNet. Experimental results on VoxCeleb show that weight quantization is effective for compressing SV models. The model size can be reduced multiple times without noticeable degradation in performance. Compression of ResNet shows more robust results than ECAPA-TDNN with lower-bitwidth quantization. Analysis of the layer weights suggests that the smooth weight distribution of ResNet may be related to its better robustness. The generalization ability of the quantized model is validated via a language-mismatched SV task. Furthermore, analysis by information probing reveals that the quantized models can retain most of the speaker-relevant knowledge learned by the original models., Comment: Accepted by INTERSPEECH2023

Deep convolutional neural networks (CNNs) have been applied to extracting speaker embeddings with significant success in speaker verification. Incorporating the attention mechanism has shown to be effective in improving the model performance. This paper presents an efficient two-dimensional convolution-based attention module, namely C2D-Att. The interaction between the convolution channel and frequency is involved in the attention calculation by lightweight convolution layers. This requires only a small number of parameters. Fine-grained attention weights are produced to represent channel and frequency-specific information. The weights are imposed on the input features to improve the representation ability for speaker modeling. The C2D-Att is integrated into a modified version of ResNet for speaker embedding extraction. Experiments are conducted on VoxCeleb datasets. The results show that C2DAtt is effective in generating discriminative attention maps and outperforms other attention methods. The proposed model shows robust performance with different scales of model size and achieves state-of-the-art results.

The capability of generating speech with specific type of emotion is desired for many applications of human-computer interaction. Cross-speaker emotion transfer is a common approach to generating emotional speech when speech with emotion labels from target speakers is not available for model training. This paper presents a novel cross-speaker emotion transfer system, named iEmoTTS. The system is composed of an emotion encoder, a prosody predictor, and a timbre encoder. The emotion encoder extracts the identity of emotion type as well as the respective emotion intensity from the mel-spectrogram of input speech. The emotion intensity is measured by the posterior probability that the input utterance carries that emotion. The prosody predictor is used to provide prosodic features for emotion transfer. The timber encoder provides timbre-related information for the system. Unlike many other studies which focus on disentangling speaker and style factors of speech, the iEmoTTS is designed to achieve cross-speaker emotion transfer via disentanglement between prosody and timbre. Prosody is considered as the main carrier of emotion-related speech characteristics and timbre accounts for the essential characteristics for speaker identification. Zero-shot emotion transfer, meaning that speech of target speakers are not seen in model training, is also realized with iEmoTTS. Extensive experiments of subjective evaluation have been carried out. The results demonstrate the effectiveness of iEmoTTS as compared with other recently proposed systems of cross-speaker emotion transfer. It is shown that iEmoTTS can produce speech with designated emotion type and controllable emotion intensity. With appropriate information bottleneck capacity, iEmoTTS is able to effectively transfer emotion information to a new speaker. Audio samples are publicly available https://patrick-g-zhang.github.io/iemotts/, Comment: Submitted to IEEE Transactions on Audio, Speech, and Language Processing

Online exams via video conference software like Zoom have been adopted in many schools due to COVID-19. While it is convenient, it is challenging for teachers to supervise online exams from simultaneously displayed student Zoom windows. In this paper, we propose iExam, an intelligent online exam monitoring and analysis system that can not only use face detection to assist invigilators in real-time student identification, but also be able to detect common abnormal behaviors (including face disappearing, rotating faces, and replacing with a different person during the exams) via a face recognition-based post-exam video analysis. To build such a novel system in its first kind, we overcome three challenges. First, we discover a lightweight approach to capturing exam video streams and analyzing them in real time. Second, we utilize the left-corner names that are displayed on each student's Zoom window and propose an improved OCR (optical character recognition) technique to automatically gather the ground truth for the student faces with dynamic positions. Third, we perform several experimental comparisons and optimizations to efficiently shorten the training and testing time required on teachers' PC. Our evaluation shows that iExam achieves high accuracy, 90.4% for real-time face detection and 98.4% for post-exam face recognition, while maintaining acceptable runtime performance. We have made iExam's source code available at https://github.com/VPRLab/iExam., Comment: This is a technical report from the Chinese University of Hong Kong

Pooling is needed to aggregate frame-level features into utterance-level representations for speaker modeling. Given the success of statistics-based pooling methods, we hypothesize that speaker characteristics are well represented in the statistical distribution over the pre-aggregation layer's output, and propose to use transport-oriented feature aggregation for deriving speaker embeddings. The aggregated representation encodes the geometric structure of the underlying feature distribution, which is expected to contain valuable speaker-specific information that may not be represented by the commonly used statistical measures like mean and variance. The original transport-oriented feature aggregation is also extended to a weighted-frame version to incorporate the attention mechanism. Experiments on speaker verification with the Voxceleb dataset show improvement over statistics pooling and its attentive variant., Comment: Accepted for presentation at INTERSPEECH 2022

Mel-scale spectrum features are used in various recognition and classification tasks on speech signals. There is no reason to expect that these features are optimal for all different tasks, including speaker verification (SV). This paper describes a learnable front-end feature extraction model. The model comprises a group of filters to transform the Fourier spectrum. Model parameters that define these filters are trained end-to-end and optimized specifically for the task of speaker verification. Compared to the standard Mel-scale filter-bank, the filters' bandwidths and center frequencies are adjustable. Experimental results show that applying the learnable acoustic front-end improves speaker verification performance over conventional Mel-scale spectrum features. Analysis on the learned filter parameters suggests that narrow-band information benefits the SV system performance. The proposed model achieves a good balance between performance and computation cost. In resource-constrained computation settings, the model significantly outperforms CNN-based learnable front-ends. The generalization ability of the proposed model is also demonstrated on different embedding extraction models and datasets.

Performance degradation caused by language mismatch is a common problem when applying a speaker verification system on speech data in different languages. This paper proposes a domain transfer network, named EDITnet, to alleviate the language-mismatch problem on speaker embeddings without requiring speaker labels. The network leverages a conditional variational auto-encoder to transfer embeddings from the target domain into the source domain. A self-supervised learning strategy is imposed on the transferred embeddings so as to increase the cosine distance between embeddings from different speakers. In the training process of the EDITnet, the embedding extraction model is fixed without fine-tuning, which renders the training efficient and low-cost. Experiments on Voxceleb and CN-Celeb show that the embeddings transferred by EDITnet outperform the un-transferred ones by around 30% with the ECAPA-TDNN512. Performance improvement can also be achieved with other embedding extraction models, e.g., TDNN, SE-ResNet34., Comment: Accepted by Interspeech2022

In this study, the Multivariate Empirical Mode Decomposition (MEMD) is applied to multichannel EEG to obtain scale-aligned intrinsic mode functions (IMFs) as input features for emotion detection. The IMFs capture local signal variation related to emotion changes. Among the extracted IMFs, the high oscillatory ones are found to be significant for the intended task. The Marginal Hilbert spectrum (MHS) is computed from the selected IMFs. A 3D convolutional neural network (CNN) is adopted to perform emotion detection with spatial-temporal-spectral feature representations that are constructed by stacking the multi-channel MHS over consecutive signal segments. The proposed approach is evaluated on the publicly available DEAP database. On binary classification of valence and arousal level (high versus low), the attained accuracies are 89.25% and 86.23% respectively, which significantly outperform previously reported systems with 2D CNN and/or conventional temporal and spectral features., Comment: Accepted in 44th International Engineering in Medicine and Biology Conference (EMBC 2022)

In this study, the Multivariate Empirical Mode Decomposition (MEMD) approach is applied to extract features from multi-channel EEG signals for mental state classification. MEMD is a data-adaptive analysis approach which is suitable particularly for multi-dimensional non-linear signals like EEG. Applying MEMD results in a set of oscillatory modes called intrinsic mode functions (IMFs). As the decomposition process is data-dependent, the IMFs vary in accordance with signal variation caused by functional brain activity. Among the extracted IMFs, it is found that those corresponding to high-oscillation modes are most useful for detecting different mental states. Non-linear features are computed from the IMFs that contribute most to mental state detection. These MEMD features show a significant performance gain over the conventional tempo-spectral features obtained by Fourier transform and Wavelet transform. The dominance of specific brain region is observed by analysing the MEMD features extracted from associated EEG channels. The frontal region is found to be most significant with a classification accuracy of 98.06%. This multi-dimensional decomposition approach upholds joint channel properties and produces most discriminative features for EEG based mental state detection., Comment: Accepted in 44th International Engineering in Medicine and Biology Conference (EMBC 2022)

The performance of child speech recognition is generally less satisfactory compared to adult speech due to limited amount of training data. Significant performance degradation is expected when applying an automatic speech recognition (ASR) system trained on adult speech to child speech directly, as a result of domain mismatch. The present study is focused on adult-to-child acoustic feature conversion to alleviate this mismatch. Different acoustic feature conversion approaches, including deep neural network based and signal processing based, are investigated and compared under a fair experimental setting, in which converted acoustic features from the same amount of labeled adult speech are used to train the ASR models from scratch. Experimental results reveal that not all of the conversion methods lead to ASR performance gain. Specifically, as a classic unsupervised domain adaptation method, the statistic matching does not show an effectiveness. A disentanglement-based auto-encoder (DAE) conversion framework is found to be useful and the approach of F0 normalization achieves the best performance. It is noted that the F0 distribution of converted features is an important attribute to reflect the conversion quality, while utilizing an adult-child deep classification model to make judgment is shown to be inappropriate., Comment: 5 pages, 4 figures, submitted to InterSpeech2022

State-of-art speaker verification (SV) systems use a back-end model to score the similarity of speaker embeddings extracted from a neural network model. The commonly used back-end models are the cosine scoring and the probabilistic linear discriminant analysis (PLDA) scoring. With the recently developed neural embeddings, the theoretically more appealing PLDA approach is found to have no advantage against or even be inferior the simple cosine scoring in terms of SV system performance. This paper presents an investigation on the relation between the two scoring approaches, aiming to explain the above counter-intuitive observation. It is shown that the cosine scoring is essentially a special case of PLDA scoring. In other words, by properly setting the parameters of PLDA, the two back-ends become equivalent. As a consequence, the cosine scoring not only inherits the basic assumptions for the PLDA but also introduces additional assumptions on the properties of input embeddings. Experiments show that the dimensional independence assumption required by the cosine scoring contributes most to the performance gap between the two methods under the domain-matched condition. When there is severe domain mismatch and the dimensional independence assumption does not hold, the PLDA would perform better than the cosine for domain adaptation., Comment: submitted to interspeech2022

This study propose a fully automated system for speech correction and accent reduction. Consider the application scenario that a recorded speech audio contains certain errors, e.g., inappropriate words, mispronunciations, that need to be corrected. The proposed system, named CorrectSpeech, performs the correction in three steps: recognizing the recorded speech and converting it into time-stamped symbol sequence, aligning recognized symbol sequence with target text to determine locations and types of required edit operations, and generating the corrected speech. Experiments show that the quality and naturalness of corrected speech depend on the performance of speech recognition and alignment modules, as well as the granularity level of editing operations. The proposed system is evaluated on two corpora: a manually perturbed version of VCTK and L2-ARCTIC. The results demonstrate that our system is able to correct mispronunciation and reduce accent in speech recordings. Audio samples are available online for demonstration https://daxintan-cuhk.github.io/CorrectSpeech/ ., Comment: Accepted by ISCSLP 2022

Recently, leveraging BERT pre-training to improve the phoneme encoder in text to speech (TTS) has drawn increasing attention. However, the works apply pre-training with character-based units to enhance the TTS phoneme encoder, which is inconsistent with the TTS fine-tuning that takes phonemes as input. Pre-training only with phonemes as input can alleviate the input mismatch but lack the ability to model rich representations and semantic information due to limited phoneme vocabulary. In this paper, we propose MixedPhoneme BERT, a novel variant of the BERT model that uses mixed phoneme and sup-phoneme representations to enhance the learning capability. Specifically, we merge the adjacent phonemes into sup-phonemes and combine the phoneme sequence and the merged sup-phoneme sequence as the model input, which can enhance the model capacity to learn rich contextual representations. Experiment results demonstrate that our proposed Mixed-Phoneme BERT significantly improves the TTS performance with 0.30 CMOS gain compared with the FastSpeech 2 baseline. The Mixed-Phoneme BERT achieves 3x inference speedup and similar voice quality to the previous TTS pre-trained model PnG BERT, Comment: Accepted by interspeech 2022

Counseling typically takes the form of spoken conversation between a therapist and a client. The empathy level expressed by the therapist is considered to be an essential quality factor of counseling outcome. This paper proposes a hierarchical recurrent network combined with two-level attention mechanisms to determine the therapist's empathy level solely from the acoustic features of conversational speech in a counseling session. The experimental results show that the proposed model can achieve an accuracy of $72.1\%$ in classifying the therapist's empathy level as being ``high" or ``low". It is found that the speech from both the therapist and the client are contributing to predicting the empathy level that is subjectively rated by an expert observer. By analyzing speaker turns assigned with high attention weights, it is observed that $2$ to $6$ consecutive turns should be considered together to provide useful clues for detecting empathy, and the observer tends to take the whole session into consideration when rating the therapist empathy, instead of relying on a few specific speaker turns., Comment: Accepted by INTERSPEECH 2022

This paper presents a macroscopic approach to automatic detection of speech sound disorder (SSD) in child speech. Typically, SSD is manifested by persistent articulation and phonological errors on specific phonemes in the language. The disorder can be detected by focally analyzing the phonemes or the words elicited by the child subject. In the present study, instead of attempting to detect individual phone- and word-level errors, we propose to extract a subject-level representation from a long utterance that is constructed by concatenating multiple test words. The speaker verification approach, and posterior features generated by deep neural network models, are applied to derive various types of holistic representations. A linear classifier is trained to differentiate disordered speech in normal one. On the task of detecting SSD in Cantonese-speaking children, experimental results show that the proposed approach achieves improved detection performance over previous method that requires fusing phone-level detection results. Using articulatory posterior features to derive i-vectors from multiple-word utterances achieves an unweighted average recall of 78.2% and a macro F1 score of 78.0%., Comment: Accepted to Interspeech 2022

In conversation-based psychotherapy, therapists use verbal techniques to help clients express thoughts and feelings, and change behavior. In particular, how well therapists convey empathy is an essential quality index of psychotherapy sessions and is associated with psychotherapy outcome. In this paper, we analyze the prosody of therapist speech and attempt to associate the therapist's speaking style with subjectively perceived empathy. An automatic speech and text processing system is developed to segment long recordings of psychotherapy sessions into pause-delimited utterances with text transcriptions. Data-driven clustering is applied to the utterances from different therapists in multiple sessions. For each cluster, a typological representation of utterance genre is derived based on quantized prosodic feature parameters. Prominent speaking styles of the therapist can be observed and interpreted from salient utterance genres that are correlated with empathy. Using the salient utterance genres, an accuracy of $71\%$ is achieved in classifying psychotherapy sessions into ``high" and ``low" empathy level. Analysis of results suggests that empathy level tends to be (1) low if therapists speak long utterances slowly or speak short utterances quickly; and (2) high if therapists talk to clients with a steady tone and volume., Comment: Accepted by INTERSPEECH 2022

Human speech production encompasses physiological processes that naturally react to physic stress. Stress caused by physical activity (PA), e.g., running, may lead to significant changes in a person's speech. The major changes are related to the aspects of pitch level, speaking rate, pause pattern, and breathiness. The extent of change depends presumably on physical fitness and well-being of the person, as well as intensity of PA. The general wellness of a person is further related to his/her physical literacy (PL), which refers to a holistic description of engagement in PA. This paper presents the development of a Cantonese speech database that contains audio recordings of speech before and after physical exercises of different intensity levels. The corpus design and data collection process are described. Preliminary results of acoustical analysis are presented to illustrate the impact of PA on pitch level, pitch range, speaking and articulation rate, and time duration of pauses. It is also noted that the effect of PA is correlated to some of the PA and PL measures., Comment: Accepted to Speech Prosody 2022

Psychoacoustic studies have shown that locally-time reversed (LTR) speech, i.e., signal samples time-reversed within a short segment, can be accurately recognised by human listeners. This study addresses the question of how well a state-of-the-art automatic speech recognition (ASR) system would perform on LTR speech. The underlying objective is to explore the feasibility of deploying LTR speech in the training of end-to-end (E2E) ASR models, as an attempt to data augmentation for improving the recognition performance. The investigation starts with experiments to understand the effect of LTR speech on general-purpose ASR. LTR speech with reversed segment duration of 5 ms - 50 ms is rendered and evaluated. For ASR training data augmentation with LTR speech, training sets are created by combining natural speech with different partitions of LTR speech. The efficacy of data augmentation is confirmed by ASR results on speech corpora in various languages and speaking styles. ASR on LTR speech with reversed segment duration of 15 ms - 30 ms is found to have lower error rate than with other segment duration. Data augmentation with these LTR speech achieves satisfactory and consistent improvement on ASR performance., Comment: Submitted to ICASSP 2022

This study aims at designing an environment-aware text-to-speech (TTS) system that can generate speech to suit specific acoustic environments. It is also motivated by the desire to leverage massive data of speech audio from heterogeneous sources in TTS system development. The key idea is to model the acoustic environment in speech audio as a factor of data variability and incorporate it as a condition in the process of neural network based speech synthesis. Two embedding extractors are trained with two purposely constructed datasets for characterization and disentanglement of speaker and environment factors in speech. A neural network model is trained to generate speech from extracted speaker and environment embeddings. Objective and subjective evaluation results demonstrate that the proposed TTS system is able to effectively disentangle speaker and environment factors and synthesize speech audio that carries designated speaker characteristics and environment attribute. Audio samples are available online for demonstration https://daxintan-cuhk.github.io/Environment-Aware-TTS/ ., Comment: Accepted by Interspeech 2022

In the development of neural text-to-speech systems, model pre-training with a large amount of non-target speakers' data is a common approach. However, in terms of ultimately achieved system performance for target speaker(s), the actual benefits of model pre-training are uncertain and unstable, depending very much on the quantity and text content of training data. This study aims to understand better why and how model pre-training can positively contribute to TTS system performance. It is postulated that the pre-training process plays a critical role in learning text-related variation in speech, while further training with the target speaker's data aims to capture the speaker-related variation. Different test sets are created with varying degrees of similarity to target speaker data in terms of text content. Experiments show that leveraging a speaker-independent TTS trained on speech data with diverse text content can improve the target speaker TTS on domain-mismatched text. We also attempt to reduce the amount of pre-training data for a new text domain and improve the data and computational efficiency. It is found that the TTS system could achieve comparable performance when the pre-training data is reduced to 1/8 of its original size.

Alzheimer's disease (AD) is a progressive neurodegenerative disease and recently attracts extensive attention worldwide. Speech technology is considered a promising solution for the early diagnosis of AD and has been enthusiastically studied. Most recent works concentrate on the use of advanced BERT-like classifiers for AD detection. Input to these classifiers are speech transcripts produced by automatic speech recognition (ASR) models. The major challenge is that the quality of transcription could degrade significantly under complex acoustic conditions in the real world. The detection performance, in consequence, is largely limited. This paper tackles the problem via tailoring and adapting pre-trained neural-network based ASR model for the downstream AD recognition task. Only bottom layers of the ASR model are retained. A simple fully-connected neural network is added on top of the tailored ASR model for classification. The heavy BERT classifier is discarded. The resulting model is light-weight and can be fine-tuned in an end-to-end manner for AD recognition. Our proposed approach takes only raw speech as input, and no extra transcription process is required. The linguistic information of speech is implicitly encoded in the tailored ASR model and contributes to boosting the performance. Experiments show that our proposed approach outperforms the best manual transcript-based RoBERTa by an absolute margin of 4.6% in terms of accuracy. Our best-performing models achieve the accuracy of 83.2% and 78.0% in the long-audio and short-audio competition tracks of the 2021 NCMMSC Alzheimer's Disease Recognition Challenge, respectively., Comment: Accepted by NCMMSC2021

The paper presents a novel approach to refining similarity scores between input utterances for robust speaker verification. Given the embeddings from a pair of input utterances, a graph model is designed to incorporate additional information from a group of embeddings representing the so-called auxiliary speakers. The relations between the input utterances and the auxiliary speakers are represented by the edges and vertices in the graph. The similarity scores are refined by iteratively updating the values of the graph's vertices using an algorithm similar to the random walk algorithm on graphs. Through this updating process, the information of auxiliary speakers is involved in determining the relation between input utterances and hence contributing to the verification process. We propose to create a set of artificial embeddings through the model training process. Utilizing the generated embeddings as auxiliary speakers, no extra data are required for the graph model in the verification stage. The proposed model is trained in an end-to-end manner within the whole system. Experiments are carried out with the Voxceleb datasets. The results indicate that involving auxiliary speakers with graph is effective to improve speaker verification performance.