Haizhou Li

• Ph.D
• Professor (Full) at National University of Singapore

It was shown that pre-trained models with self-supervised learning (SSL) techniques are effective in various downstream speech tasks. However, most such models are trained on single-speaker speech data, limiting their effectiveness in mixture speech. This motivates us to explore pre-training on mixture speech. This work presents SA-WavLM, a novel p...

Emotion and Intent Joint Understanding in Multimodal Conversation (MC-EIU) aims to decode the semantic information manifested in a multimodal conversational history, while inferring the emotions and intents simultaneously for the current utterance. MC-EIU is enabling technology for many human-computer interfaces. However, there is a lack of availab...

Speech encompasses a wealth of information, including but not limited to content, paralinguistic, and environmental information. This comprehensive nature of speech significantly impacts communication and is crucial for human-computer interaction. Chat-Oriented Large Language Models (LLMs), known for their general-purpose assistance capabilities, h...

The use of Transformer architectures has facilitated remarkable progress in speech enhancement. Training Transformers using substantially long speech utterances is often infeasible as self-attention suffers from quadratic complexity. It is a critical and unexplored challenge for a Transformer-based speech enhancement model to learn from short speec...

Synthesizing speech across different accents while preserving the speaker identity is essential for various real-world customer applications. However, the individual and accurate modeling of accents and speakers in a text-to-speech (TTS) system is challenging due to the complexity of accent variations and the intrinsic entanglement between the acce...

Keyword Spotting (KWS) is essential in edge computing requiring rapid and energy-efficient responses. Spiking Neural Networks (SNNs) are well-suited for KWS for their efficiency and temporal capacity for speech. To further reduce the latency and energy consumption, this study introduces ED-sKWS, an SNN-based KWS model with an early-decision mechani...

Traditional speaker diarization seeks to detect ``who spoke when'' according to speaker characteristics. Extending to target speech diarization, we detect ``when target event occurs'' according to the semantic characteristics of speech. We propose a novel Multimodal Target Speech Diarization (MM-TSD) framework, which accommodates diverse and multi-...

Audio language models have recently emerged as a promising approach for various audio generation tasks, relying on audio tokenizers to encode waveforms into sequences of discrete symbols. Audio tokenization often poses a necessary compromise between code bitrate and reconstruction accuracy. When dealing with low-bitrate audio codes, language models...

Partially manipulating a sentence can greatly change its meaning. Recent work shows that countermeasures (CMs) trained on partially spoofed audio can effectively detect such spoofing. However, the current understanding of the decision-making process of CMs is limited. We utilize Grad-CAM and introduce a quantitative analysis metric to interpret CMs...

The automatic evaluation of natural language generation (NLG) systems presents a long-lasting challenge. Recent studies have highlighted various neural metrics that align well with human evaluations. Yet, the robustness of these evaluators against adversarial perturbations remains largely under-explored due to the unique challenges in obtaining adv...

It remains a challenge to effectively control the emotion rendering in text-to-speech (TTS) synthesis. Prior studies have primarily focused on learning a global prosodic representation at the utterance level, which strongly correlates with linguistic prosody. Our goal is to construct a hierarchical emotion distribution (ED) that effectively encapsu...

The identification of sensory cues associated with potential opportunities and dangers is frequently complicated by unrelated events that separate useful cues by long delays. As a result, it remains a challenging task for state-of-the-art spiking neural networks (SNNs) to establish long-term temporal dependency between distant cues. To address this...

Prior studies on audio-visual speech recognition typically assume the visibility of speaking lips, ignoring the fact that visual occlusion occurs in real-world videos, thus adversely affecting recognition performance. To address this issue, we propose a framework that restores occluded lips in a video by utilizing both the video itself and the corr...

Automatic evaluation is an integral aspect of dialogue system research. The traditional reference-based NLG metrics are generally found to be unsuitable for dialogue assessment. Consequently, recent studies have suggested various unique, reference-free neural metrics that better align with human evaluations. Notably among them, large language model...

Conversational Speech Synthesis (CSS) aims to accurately express an utterance with the appropriate prosody and emotional inflection within a conversational setting. While recognising the significance of CSS task, the prior studies have not thoroughly investigated the emotional expressiveness problems due to the scarcity of emotional conversational...

Self-supervised learning (SSL) is an effective way of learning rich and transferable speech representations from unlabeled data to benefit downstream tasks. However, effectively incorporating a pre-trained SSL model into an automatic speech recognition (ASR) system remains challenging. In this paper, we propose a network architecture with light-wei...

This paper presents an accented text-to-speech (TTS) synthesis framework with limited training data. We study two aspects concerning accent rendering: phonetic (phoneme difference) and prosodic (pitch pattern and phoneme duration) variations. The proposed accented TTS framework consists of two models: an accented front-end for grapheme-to-phoneme (...

Decoding auditory attention from brain activities, such as electroencephalography (EEG), sheds light on solving the machine cocktail party problem. However, effective representation of EEG signals remains a challenge. One of the reasons is that the current feature extraction techniques have not fully exploited the spatial information along the EEG...

Multimodal emotion recognition (MER) aims to understand the way that humans express their emotions by exploring complementary information across modalities. However, it is hard to guarantee that full-modality data is always available in real-world scenarios. To deal with missing modalities, researchers focused on meaningful joint multimodal represe...

Accented text-to-speech (TTS) synthesis seeks to generate speech with an accent (L2) as a variant of the standard version (L1), which is challenging as L2 is different from L1 in terms of phonetic rendering and prosody pattern (pitch, energy, and duration variance, etc.). Accented TTS has several significant real-world applications, such as languag...

Self-supervised pre-trained speech models were shown effective for various downstream speech processing tasks. Since they are mainly pre-trained to map input speech to pseudo-labels, the resulting representations are only effective for the type of pre-train data used, either clean or mixture speech. With the idea of selective auditory attention, we...

The residual neural networks (ResNet) demonstrate the impressive performance in automatic speaker verification (ASV). They treat the time and frequency dimensions equally, following the default stride configuration designed for image recognition, where the horizontal and vertical axes exhibit similarities. This approach ignores the fact that time a...

Recently, brain-inspired spiking neural networks (SNNs) have demonstrated promising capabilities in solving pattern recognition tasks. However, these SNNs are grounded on homogeneous neurons that utilize a uniform neural coding for information representation. Given that each neural coding scheme possesses its own merits and drawbacks, these SNNs en...

For speaker recognition, it is difficult to extract an accurate speaker representationfrom speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker traits andcontent variability in speech. It is realized with the use of three Gaussian inferencelayers, each consis...

Emotional speech synthesis aims to synthesize human voices with various emotional effects. The current studies are mostly focused on imitating an averaged style belonging to a specific emotion type. In this paper, we seek to generate speech with a mixture of emotions at run-time. We propose a novel formulation that measures the relative difference...

Electroencephalography (EEG) related research faces a significant challenge of subject independence due to the variation in brain signals and responses among individuals. While deep learning models hold promise in addressing this challenge, their effectiveness depends on large datasets for training and generalization across participants. To overcom...

Emotional voice conversion (EVC) traditionally targets the transformation of spoken utterances from one emotional state to another, with previous research mainly focusing on discrete emotion categories. This paper departs from the norm by introducing a novel perspective: a nuanced rendering of mixed emotions and enhancing control over emotional exp...

\textit{Objective:} Conventional EEG-based auditory attention detection (AAD) is achieved by comparing the time-varying speech stimuli and the elicited EEG signals. However, in order to obtain reliable correlation values, these methods necessitate a long decision window, resulting in a long detection latency. Humans have a remarkable ability to rec...

The identification of sensory cues associated with potential opportunities and dangers is frequently complicated by unrelated events that separate useful cues by long delays. As a result, it remains a challenging task for state-of-the-art spiking neural networks (SNNs) to establish long-term temporal dependency between distant cues. To address this...

Humans show a remarkable ability in solving the cocktail party problem. Decoding auditory attention from the brain signals is a major step toward the development of bionic ears emulating human capabilities. Electroencephalography (EEG)-based auditory attention detection (AAD) has attracted considerable interest recently. Despite much progress, the...

Humans possess the remarkable ability to selectively attend to a single speaker amidst competing voices and background noise, known as selective auditory attention. Recent studies in auditory neuroscience indicate a strong correlation between the attended speech signal and the corresponding brain's elicited neuronal activities, which the latter can...

Acoustic word embeddings (AWEs) aims to map a variable-length speech segment into a fixed-dimensional representation. High-quality AWEs should be invariant to variations, such as duration, pitch and speaker. In this paper, we introduce a novel self-supervised method to learn robust AWEs from a large-scale unlabelled speech corpus. Our model, named...

The identification of sensory cues associated with potential opportunities and dangers is frequently complicated by unrelated events that separate useful cues by long delays. As a result, it remains a challenging task for state-of-the-art spiking neural networks (SNNs) to identify long-term temporal dependencies since bridging the temporal gap nece...

The goal of Automatic Voice Over (AVO) is to generate speech in sync with a silent video given its text script. Recent AVO frameworks built upon text-to-speech synthesis (TTS) have shown impressive results. However, the current AVO learning objective of acoustic feature reconstruction brings in indirect supervision for inter-modal alignment learnin...

The biological neural systems evolved to adapt to ecological environment for efficiency and effectiveness, wherein neurons with heterogeneous structures and rich dynamics are optimized to accomplish complex cognitive tasks. Most of the current research of biologically inspired spiking neural networks (SNNs) are, however, grounded on a homogeneous n...

Audio Deepfake Detection (ADD) aims to detect the fake audio generated by text-to-speech (TTS), voice conversion (VC) and replay, etc., which is an emerging topic. Traditionally we take the mono signal as input and focus on robust feature extraction and effective classifier design. However, the dual-channel stereo information in the audio signal al...

The use of Transformer represents a recent success in speech enhancement. However, as its core component, self-attention suffers from quadratic complexity, which is computationally prohibited for long speech recordings. Moreover, it allows each time frame to attend to all time frames, neglecting the strong local correlations of speech signals. This...

This paper presents an accented text-to-speech (TTS) synthesis framework with limited training data. We study two aspects concerning accent rendering: phonetic (phoneme difference) and prosodic (pitch pattern and phoneme duration) variations. The proposed accented TTS framework consists of two models: an accented front-end for grapheme-to-phoneme (...

Talking face generation, also known as speech-to-lip generation, reconstructs facial motions concerning lips given coherent speech input. The previous studies revealed the importance of lip-speech synchronization and visual quality. Despite much progress, they hardly focus on the content of lip movements i.e., the visual intelligibility of the spok...

End-to-end time-domain speech separation with masking strategy has shown its performance advantage, where a 1-D convolutional layer is used as the speech encoder to encode a sliding window of waveform to a latent feature representation, i.e. an embedding vector. A large window leads to low resolution in the speech processing, on the other hand, a s...

Chatbots are expected to be knowledgeable across multiple domains, e.g. for daily chit-chat, exchange of information, and grounding in emotional situations. To effectively measure the quality of such conversational agents, a model-based automatic dialogue evaluation metric (ADEM) is expected to perform well across multiple domains. Despite signific...

We study a novel neural speaker encoder and its training strategies for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed dimensional speaker embedding from a spoken utterance of variable length. Contrastive learning is a typical self-supervised learning technique. However, the contrastive lear...

Accent Conversion (AC) seeks to change the accent of speech from one (source) to another (target) while preserving the speech content and speaker identity. However, many existing AC approaches rely on source-target parallel speech data during training or reference speech at run-time. We propose a novel accent conversion framework without the need f...

Lyrics transcription of polyphonic music is challenging as the background music affects lyrics intelligibility. Typically, lyrics transcription can be performed by a two-step pipeline, i.e. a singing vocal extraction front end, followed by a lyrics transcriber back end, where the front end and back end are trained separately. Such a two-step pipeli...

This paper presents a framework towards multi-accent neural text-to-speech synthesis for zero-shot multi-speaker, which employs an encoder-decoder architecture and an accent classifier to control the pronunciation variation from the encoder. The encoder and decoder are pre-trained on a large-scale multi-speaker corpus. The accent-informed encoder o...

This paper introduces the Tenth Dialog System Technology Challenge (DSTC-10). This edition of the DSTC focuses on applying end-to-end dialog technologies for five distinct tasks in dialog systems, namely 1. Incorporation of Meme images into open domain dialogs, 2. Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations, 3. Situat...

Cross-modal Retrieval (CMR) is formulated for the scenarios where the queries and retrieval results are of different modalities. Existing CMR studies mainly focus on the common contextualized information between text transcripts and images, and the synchronized event information in audio-visual recordings. Different from all previous works, in this...

The biological neurons use precise spike times, in addition to the spike firing rate, to communicate with each other. The time-to-first-spike (TTFS) coding is inspired by such biological observation. However, there is a lack of effective solutions for training TTFS-based spiking neural network (SNN). In this paper, we put forward a simple yet effec...

For the development of neuro-steered hearing aids, it is important to study the relationship between a speech stimulus and the elicited EEG response of a human listener. The recent Auditory EEG Decoding Challenge 2023 (Signal Processing Grand Challenge, IEEE International Conference on Acoustics, Speech and Signal Processing) dealt with this relati...

Accent Conversion (AC) seeks to change the accent of speech from one (source) to another (target) while preserving the speech content and speaker identity. However, many AC approaches rely on source-target parallel speech data. We propose a novel accent conversion framework without the need of parallel data. Specifically, a text-to-speech (TTS) sys...

Chatbots are expected to be knowledgeable across multiple domains, e.g. for daily chit-chat, exchange of information, and grounding in emotional situations. To effectively measure the quality of such conversational agents, a model-based automatic dialogue evaluation metric (ADEM) is expected to perform well across multiple domains. Despite signific...

In neural speech enhancement, a mismatch exists between the training objective, i.e., Mean-Square Error (MSE), and perceptual quality evaluation metrics, i.e., perceptual evaluation of speech quality and short-time objective intelligibility. We propose a novel reinforcement learning algorithm and network architecture, which incorporate a non-differ...

This manuscript describes the I4U submission to the 2020 NIST Speaker Recognition Evaluation (SRE'20) Conversational Telephone Speech (CTS) Challenge. The I4U's submission was resulted from active collaboration among researchers across eight research teams - I$^2$R (Singapore), UEF (Finland), VALPT (Italy, Spain), NEC (Japan), THUEE (China), LIA (F...

Recently, there is a surge of interest in applying pre-trained language models (Pr-LM) in automatic open-domain dialog evaluation. Pr-LMs offer a promising direction for addressing the multi-domain evaluation challenge. Yet, the impact of different Pr-LMs on the performance of automatic metrics is not well-understood. This paper examines eight diff...

The speaker extraction technique seeks to single out the voice of a target speaker from the interfering voices in a speech mixture. Typically an auxiliary reference of the target speaker is used to form voluntary attention. Either a pre-recorded utterance or a synchronized lip movement in a video clip can serve as the auxiliary reference. The use o...

Neural network-based speaker recognition has achieved significant improvement in recent years. A robust speaker representation learns meaningful knowledge from both hard and easy samples in the training set to achieve good performance. However, noisy samples (i.e., with wrong labels) in the training set induce confusion and cause the network to lea...

Multimodal emotion recognition leverages complementary information across modalities to gain performance. However, we cannot guarantee that the data of all modalities are always present in practice. In the studies to predict the missing data across modalities, the inherent difference between heterogeneous modalities, namely the modality gap, presen...

Accented text-to-speech (TTS) synthesis seeks to generate speech with an accent (L2) as a variant of the standard version (L1). How to control the intensity of accent in the process of TTS is a very interesting research direction, and has attracted more and more attention. Recent work design a speaker-adversarial loss to disentangle the speaker and...

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance of various length. Contrastive learning is a typical self-supervised learning technique. However, the quality...

Conversational Text-to-Speech (TTS) aims to synthesis an utterance with the right linguistic and affective prosody in a conversational context. The correlation between the current utterance and the dialogue history at the utterance level was used to improve the expressiveness of synthesized speech. However, the fine-grained information in the dialo...

Recent model-based reference-free metrics for open-domain dialogue evaluation exhibit promising correlations with human judgment. However, they either perform turn-level evaluation or look at a single dialogue quality dimension. One would expect a good evaluation metric to assess multiple quality dimensions at the dialogue level. To this end, we ar...

Spiking neural networks (SNNs) are shown to be more biologically plausible and energy efficient over their predecessors. However, there is a lack of an efficient and generalized training method for deep SNNs, especially for deployment on analog computing substrates. In this paper, we put forward a generalized learning rule, termed Local Tandem Lear...

Accented text-to-speech (TTS) synthesis seeks to generate speech with an accent (L2) as a variant of the standard version (L1). Accented TTS synthesis is challenging as L2 is different from L1 in both in terms of phonetic rendering and prosody pattern. Furthermore, there is no easy solution to the control of the accent intensity in an utterance. In...