Tan Lee

Chinese University of Hong Kong | CUHK · Department of Electronic Engineering

This study explores speaker-specific features encoded in speaker embeddings and intermediate layers of speech self-supervised learning (SSL) models. By utilising a probing method, we analyse features such as pitch, tempo, and energy across prominent speaker embedding models and speech SSL models, including HuBERT, WavLM, and Wav2vec 2.0. The result...

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 investiga...

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 counselin...

This paper presents a user-driven approach for synthesizing highly specific target voices based on user feedback, which is particularly beneficial for speech-impaired individuals who wish to recreate their lost voices but lack prior recordings. Specifically, we leverage the neural analysis and synthesis framework to construct a low-dimensional, yet...

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 utte...

Speech sound disorder (SSD) in children is manifested by persistent articulation and phonological errors on specific phonemes of a language. Automatic SSD detection can be done using features extracted from deep neural network models. Interpretability of such learned features is a major concern. Motivated by clinical knowledge, the use of duration...

This study investigates the relationships between therapists’ use of discourse particles and therapist empathy. Discourse particles, commonly found in non-English languages, are verbal elements that constitute metacommunication by encoding speakers’ emotions and attitudes, which are typically expressed by nonverbal behaviors (e.g., intonation, tone...

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 synthesi...

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 speak...

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 value...

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. Ideally, the enhancement model should be able to tackle mu...

The capability of generating speech with a specific type of emotion is desired for many human-computer interaction applications. Cross-speaker emotion transfer is a common approach to generating emotional speech when speech data with emotion labels from target speakers is not available for model training. This paper presents a novel cross-speaker e...

Introduction Previous studies explored the preferences for therapists’ attire and office setting based on initial impressions as a reference for the formality in psychotherapy. This study examines the formality of psychotherapy by investigating therapists’ and clients’ use of discourse particles, the linguistic marker and quantifier of the formalit...

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. Thi...

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 cor...

DNN-based models achieve high performance in the speaker verification (SV) task with substantial computation costs. The model size is an essential concern in applying models on resource-constrained devices, while model compression for SV models has not been studied extensively in previous works. Weight quantization is exploited to compress DNN-base...

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 in...

Examine age-related modulation of EEG microstates parameters with both broadband and narrowband microstates analyses. *Excellent Presentation Award

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 emoti...

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...

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 conditiona...

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 th...

This study developed a speech database for assessing one of the elements of physical literacy—physical competence. Thirty-one healthy and native Cantonese speakers were instructed to read a material aloud after various exercises. The speech database contained four types of speech, which were collected at rest and after three exercises of the Canadi...

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...

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 app...

This study extends our previous work on text-based speech editing to developing 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...

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 a...

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 pres...

Despite the widespread utilization of deep neural networks (DNNs) for speech emotion recognition (SER), they are severely restricted due to the paucity of labeled data for training. Recently, segment-based approaches for SER have been evolving, which train backbone networks on shorter segments instead of whole utterances, and thus naturally augment...

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 pres...

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...

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 ut...

Speech sound disorder (SSD) refers to a type of developmental disorder in young children who encounter persistent difficulties in producing certain speech sounds at the expected age. Consonant errors are the major indicator of SSD in clinical assessment. Previous studies on automatic assessment of SSD revealed that detection of speech errors concer...

Acoustic scene classification (ASC) aims to identify the type of scene (environment) in which a given audio signal is recorded. The log-mel feature and convolutional neural network (CNN) have recently become the most popular time-frequency (TF) feature representation and classifier in ASC. An audio signal recorded in a scene may include various sou...

This paper describes a novel design of a neural network-based speech generation model for learning prosodic representation.The problem of representation learning is formulated according to the information bottleneck (IB) principle. A modified VQ-VAE quantized layer is incorporated in the speech generation model to control the IB capacity and adjust...

This paper presents the design, implementation and evaluation of a speech editing system, named EditSpeech, which allows a user to perform deletion, insertion and replacement of words in a given speech utterance, without causing audible degradation in speech quality and naturalness. The EditSpeech system is developed upon a neural text-to-speech (N...

Speech sound disorder (SSD) refers to a type of developmental disorder in young children who encounter persistent difficulties in producing certain speech sounds at the expected age. Consonant errors are the major indicator of SSD in clinical assessment. Previous studies on automatic assessment of SSD revealed that detection of speech errors concer...

A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that is often attributable to speaker differences. Speaker adaptation techniques play a vital role to reduce the mismatch. Model-based speaker adaptation approaches often require sufficient amounts of target speaker data to ensure robustness. Wh...

Despite the widespread utilization of deep neural networks (DNNs) for speech emotion recognition (SER), they are severely restricted due to the paucity of labeled data for training. Recently, segment-based approaches for SER have been evolving, which train backbone networks on shorter segments instead of whole utterances, and thus naturally augment...

This paper presents the CUHK-EE voice cloning system for ICASSP 2021 M2VoC challenge. The challenge provides two Mandarin speech corpora: the AIShell-3 corpus of 218 speakers with noise and reverberation and the MST corpus including high-quality speech of one male and one female speakers. 100 and 5 utterances of 3 target speakers in different voice...

A key task for speech recognition systems is to reduce the mismatch between the training and evaluation data that is often attributable to speaker differences. To this end, speaker adaptation techniques play a vital role to reduce the mismatch. Model-based speaker adaptation approaches often require sufficient amounts of target speaker data to ensu...

Spoken term discovery from untranscribed speech audio could be achieved via a two-stage process. In the first stage, the unlabelled speech is decoded into a sequence of subword units that are learned and modelled in an unsupervised manner. In the second stage, partial sequence matching and clustering are performed on the decoded subword sequences,...

This technical report describes our submission to the 2021 SLT Children Speech Recognition Challenge (CSRC) Track 1. Our approach combines the use of a joint CTC-attention end-to-end (E2E) speech recognition framework, transfer learning, data augmentation and development of various language models. Procedures of data pre-processing, the background...

This paper presents an extension of the Tacotron 2 end-to-end speech synthesis architecture, which aims to learn syllable-level discrete prosodic representations from speech data. The learned representations can be used for transferring or controlling prosody in expressive speech generation. The proposed design starts with a syllable-level text enc...

The present study tackles the problem of automatically discovering spoken keywords from untranscribed audio archives without requiring word-by-word speech transcription by automatic speech recognition (ASR) technology. The problem is of practical significance in many applications of speech analytics, including those concerning low-resource language...

Human emotional speech is, by its very nature, a variant signal. This results in dynamics intrinsic to automatic emotion classification based on speech. In this work, we explore a spectral decomposition method stemming from fluid-dynamics, known as Dynamic Mode Decomposition (DMD), to computationally represent and analyze the global utterance-level...

Categorical speech emotion recognition is typically performed as a sequence-to-label problem, i.e., to determine the discrete emotion label of the input utterance as a whole. One of the main challenges in practice is that most of the existing emotion corpora do not give ground truth labels for each segment; instead, we only have labels for whole ut...

Human emotions are inherently ambiguous and impure. When designing systems to anticipate human emotions based on speech, the lack of emotional purity must be considered. However, most of the current methods for speech emotion classification rest on the consensus, e.g., one single hard label for an utterance. This labeling principle imposes challeng...

Conventional automatic assessment of pathological speech usually follows two main steps: (1) extraction of pathology-specific features; (2) classification or regression on extracted features. Given the great variety of speech and language disorders, feature design is never a straightforward task, and yet it is most crucial to the performance of ass...

Acoustic scene classification is the task of identifying the type of acoustic environment in which a given audio signal is recorded. The signal is a mixture of sound events with various characteristics. In-depth and focused analysis is needed to find out the most representative sound patterns for recognizing and differentiating the scenes. In this...