arXiv subjects

Haizhou Li

Publications and source records attributed to Haizhou Li.

At least 91 records · Page 5Linked to original sources

arXiv2025

Human-Inspired Computing for Robust and Efficient Audio-Visual Speech Recognition

Humans naturally perform audiovisual speech recognition (AVSR), enhancing the accuracy and robustness by integrating auditory and visual information. Spiking neural networks (SNNs), which mimic the brain's information-processing mechanisms, are well-suited for emulating the human capability of AVSR. Despite their potential, research on SNNs for AVSR is scarce, with most existing audio-visual multimodal methods focused on object or digit recognition. These models simply integrate features from both modalities, neglecting their unique characteristics and interactions. Additionally, they often rely on future information for current processing, which increases recognition latency and limits real-time applicability. Inspired by human speech perception, this paper proposes a novel human-inspired SNN named HI-AVSNN for AVSR, incorporating three key characteristics: cueing interaction, causal processing and spike activity. For cueing interaction, we propose a visual-cued auditory attention module (VCA2M) that leverages visual cues to guide attention to auditory features. We achieve causal processing by aligning the SNN's temporal dimension with that of visual and auditory features and applying temporal masking to utilize only past and current information. To implement spike activity, in addition to using SNNs, we leverage the event camera to capture lip movement as spikes, mimicking the human retina and providing efficient visual data. We evaluate HI-AVSNN on an audiovisual speech recognition dataset combining the DVS-Lip dataset with its corresponding audio samples. Experimental results demonstrate the superiority of our proposed fusion method, outperforming existing audio-visual SNN fusion methods and achieving a 2.27% improvement in accuracy over the only existing SNN-based AVSR method.

cs.MM↗

arXiv2025

Interpolating Speaker Identities in Embedding Space for Data Expansion

The success of deep learning-based speaker verification systems is largely attributed to access to large-scale and diverse speaker identity data. However, collecting data from more identities is expensive, challenging, and often limited by privacy concerns. To address this limitation, we propose INSIDE (Interpolating Speaker Identities in Embedding Space), a novel data expansion method that synthesizes new speaker identities by interpolating between existing speaker embeddings. Specifically, we select pairs of nearby speaker embeddings from a pretrained speaker embedding space and compute intermediate embeddings using spherical linear interpolation. These interpolated embeddings are then fed to a text-to-speech system to generate corresponding speech waveforms. The resulting data is combined with the original dataset to train downstream models. Experiments show that models trained with INSIDE-expanded data outperform those trained only on real data, achieving 3.06\% to 5.24\% relative improvements. While INSIDE is primarily designed for speaker verification, we also validate its effectiveness on gender classification, where it yields a 13.44\% relative improvement. Moreover, INSIDE is compatible with other augmentation techniques and can serve as a flexible, scalable addition to existing training pipelines.

eess.AS↗

arXiv2025

ShizhenGPT: Towards Multimodal LLMs for Traditional Chinese Medicine

Despite the success of large language models (LLMs) in various domains, their potential in Traditional Chinese Medicine (TCM) remains largely underexplored due to two critical barriers: (1) the scarcity of high-quality TCM data and (2) the inherently multimodal nature of TCM diagnostics, which involve looking, listening, smelling, and pulse-taking. These sensory-rich modalities are beyond the scope of conventional LLMs. To address these challenges, we present ShizhenGPT, the first multimodal LLM tailored for TCM. To overcome data scarcity, we curate the largest TCM dataset to date, comprising 100GB+ of text and 200GB+ of multimodal data, including 1.2M images, 200 hours of audio, and physiological signals. ShizhenGPT is pretrained and instruction-tuned to achieve deep TCM knowledge and multimodal reasoning. For evaluation, we collect recent national TCM qualification exams and build a visual benchmark for Medicinal Recognition and Visual Diagnosis. Experiments demonstrate that ShizhenGPT outperforms comparable-scale LLMs and competes with larger proprietary models. Moreover, it leads in TCM visual understanding among existing multimodal LLMs and demonstrates unified perception across modalities like sound, pulse, smell, and vision, paving the way toward holistic multimodal perception and diagnosis in TCM. Datasets, models, and code are publicly available. We hope this work will inspire further exploration in this field.

cs.CL↗

arXiv2025

UniTalker: Conversational Speech-Visual Synthesis

Conversational Speech Synthesis (CSS) is a key task in the user-agent interaction area, aiming to generate more expressive and empathetic speech for users. However, it is well-known that "listening" and "eye contact" play crucial roles in conveying emotions during real-world interpersonal communication. Existing CSS research is limited to perceiving only text and speech within the dialogue context, which restricts its effectiveness. Moreover, speech-only responses further constrain the interactive experience. To address these limitations, we introduce a Conversational Speech-Visual Synthesis (CSVS) task as an extension of traditional CSS. By leveraging multimodal dialogue context, it provides users with coherent audiovisual responses. To this end, we develop a CSVS system named UniTalker, which is a unified model that seamlessly integrates multimodal perception and multimodal rendering capabilities. Specifically, it leverages a large-scale language model to comprehensively understand multimodal cues in the dialogue context, including speaker, text, speech, and the talking-face animations. After that, it employs multi-task sequence prediction to first infer the target utterance's emotion and then generate empathetic speech and natural talking-face animations. To ensure that the generated speech-visual content remains consistent in terms of emotion, content, and duration, we introduce three key optimizations: 1) Designing a specialized neural landmark codec to tokenize and reconstruct facial expression sequences. 2) Proposing a bimodal speech-visual hard alignment decoding strategy. 3) Applying emotion-guided rendering during the generation stage. Comprehensive objective and subjective experiments demonstrate that our model synthesizes more empathetic speech and provides users with more natural and emotionally consistent talking-face animations.

eess.AS↗

arXiv2025

Accent Normalization Using Self-Supervised Discrete Tokens with Non-Parallel Data

Accent normalization converts foreign-accented speech into native-like speech while preserving speaker identity. We propose a novel pipeline using self-supervised discrete tokens and non-parallel training data. The system extracts tokens from source speech, converts them through a dedicated model, and synthesizes the output using flow matching. Our method demonstrates superior performance over a frame-to-frame baseline in naturalness, accentedness reduction, and timbre preservation across multiple English accents. Through token-level phonetic analysis, we validate the effectiveness of our token-based approach. We also develop two duration preservation methods, suitable for applications such as dubbing.

eess.AS↗

arXiv2025

Human Demonstrations are Generalizable Knowledge for Robots

Learning from human demonstrations is an emerging trend for designing intelligent robotic systems. However, previous methods typically regard videos as instructions, simply dividing them into action sequences for robotic repetition, which poses obstacles to generalization to diverse tasks or object instances. In this paper, we propose a different perspective, considering human demonstration videos not as mere instructions, but as a source of knowledge for robots. Motivated by this perspective and the remarkable comprehension and generalization capabilities exhibited by large language models (LLMs), we propose DigKnow, a method that DIstills Generalizable KNOWledge with a hierarchical structure. Specifically, DigKnow begins by converting human demonstration video frames into observation knowledge. This knowledge is then subjected to analysis to extract human action knowledge and further distilled into pattern knowledge compassing task and object instances, resulting in the acquisition of generalizable knowledge with a hierarchical structure. In settings with different tasks or object instances, DigKnow retrieves relevant knowledge for the current task and object instances. Subsequently, the LLM-based planner conducts planning based on the retrieved knowledge, and the policy executes actions in line with the plan to achieve the designated task. Utilizing the retrieved knowledge, we validate and rectify planning and execution outcomes, resulting in a substantial enhancement of the success rate. Experimental results across a range of tasks and scenes demonstrate the effectiveness of this approach in facilitating real-world robots to accomplish tasks with the knowledge derived from human demonstrations.

cs.RO↗

arXiv2025

Multi-Step Prediction and Control of Hierarchical Emotion Distribution in Text-to-Speech Synthesis

We investigate hierarchical emotion distribution (ED) for achieving multi-level quantitative control of emotion rendering in text-to-speech synthesis (TTS). We introduce a novel multi-step hierarchical ED prediction module that quantifies emotion variance at the utterance, word, and phoneme levels. By predicting emotion variance in a multi-step manner, we leverage global emotional context to refine local emotional variations, thereby capturing the intrinsic hierarchical structure of speech emotion. Our approach is validated through its integration into a variance adaptor and an external module design compatible with various TTS systems. Both objective and subjective evaluations demonstrate that the proposed framework significantly enhances emotional expressiveness and enables precise control of emotion rendering across multiple speech granularities.

cs.SD↗

arXiv2025

Long-Context Modeling Networks for Monaural Speech Enhancement: A Comparative Study

Advanced long-context modeling backbone networks, such as Transformer, Conformer, and Mamba, have demonstrated state-of-the-art performance in speech enhancement. However, a systematic and comprehensive comparative study of these backbones within a unified speech enhancement framework remains lacking. In addition, xLSTM, a more recent and efficient variant of LSTM, has shown promising results in language modeling and as a general-purpose vision backbone. In this paper, we investigate the capability of xLSTM in speech enhancement, and conduct a comprehensive comparison and analysis of the Transformer, Conformer, Mamba, and xLSTM backbones within a unified framework, considering both causal and noncausal configurations. Overall, xLSTM and Mamba achieve better performance than Transformer and Conformer. Mamba demonstrates significantly superior training and inference efficiency, particularly for long speech inputs, whereas xLSTM suffers from the slowest processing speed.

eess.AS↗

arXiv2025

Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles

User simulators are crucial for replicating human interactions with dialogue systems, supporting both collaborative training and automatic evaluation, especially for large language models (LLMs). However, current role-playing methods face challenges such as a lack of utterance-level authenticity and user-level diversity, often hindered by role confusion and dependence on predefined profiles of well-known figures. In contrast, direct simulation focuses solely on text, neglecting implicit user traits like personality and conversation-level consistency. To address these issues, we introduce the User Simulator with Implicit Profiles (USP), a framework that infers implicit user profiles from human-machine interactions to simulate personalized and realistic dialogues. We first develop an LLM-driven extractor with a comprehensive profile schema, then refine the simulation using conditional supervised fine-tuning and reinforcement learning with cycle consistency, optimizing at both the utterance and conversation levels. Finally, a diverse profile sampler captures the distribution of real-world user profiles. Experimental results show that USP outperforms strong baselines in terms of authenticity and diversity while maintaining comparable consistency. Additionally, using USP to evaluate LLM on dynamic multi-turn aligns well with mainstream benchmarks, demonstrating its effectiveness in real-world applications.

cs.CL↗

arXiv2025

Do We Really Need GNNs with Explicit Structural Modeling? MLPs Suffice for Language Model Representations

Explicit structural information has been proven to be encoded by Graph Neural Networks (GNNs), serving as auxiliary knowledge to enhance model capabilities and improve performance in downstream NLP tasks. However, recent studies indicate that GNNs fail to fully utilize structural information, whereas Multi-Layer Perceptrons (MLPs), despite lacking the message-passing mechanisms inherent to GNNs, exhibit a surprising ability in structure-aware tasks. Motivated by these findings, this paper introduces a comprehensive probing framework from an information-theoretic perspective. The framework is designed to systematically assess the role of explicit structural modeling in enhancing language model (LM) representations and to investigate the potential of MLPs as efficient and scalable alternatives to GNNs. We extend traditional probing classifiers by incorporating a control module that allows for selective use of either the full GNN model or its decoupled components, specifically, the message-passing and feature-transformation operations.This modular approach isolates and assesses the individual contributions of these operations, avoiding confounding effects from the complete GNN architecture. Using the Edge Probing Suite, a diagnostic tool for evaluating the linguistic knowledge encoded in LMs, we find that MLPs, when used as feature-transformation modules, consistently improve the linguistic knowledge captured in LM representations across different architectures. They effectively encode both syntactic and semantic patterns. Similarly, GNNs that incorporate feature-transformation operations show beneficial effects. In contrast, models that rely solely on message-passing operations tend to underperform, often leading to negative impacts on probing task performance.

cs.CL↗

arXiv2025

Hierarchical Control of Emotion Rendering in Speech Synthesis

Emotional text-to-speech synthesis (TTS) aims to generate realistic emotional speech from input text. However, quantitatively controlling multi-level emotion rendering remains challenging. In this paper, we propose a flow-matching based emotional TTS framework with a novel approach for emotion intensity modeling to facilitate fine-grained control over emotion rendering at the phoneme, word, and utterance levels. We introduce a hierarchical emotion distribution (ED) extractor that captures a quantifiable ED embedding across different speech segment levels. Additionally, we explore various acoustic features and assess their impact on emotion intensity modeling. During TTS training, the hierarchical ED embedding effectively captures the variance in emotion intensity from the reference audio and correlates it with linguistic and speaker information. The TTS model not only generates emotional speech during inference, but also quantitatively controls the emotion rendering over the speech constituents. Both objective and subjective evaluations demonstrate the effectiveness of our framework in terms of speech quality, emotional expressiveness, and hierarchical emotion control.

cs.SD↗

arXiv2025

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms

Speech pre-processing techniques such as denoising, de-reverberation, and separation, are commonly employed as front-ends for various downstream speech processing tasks. However, these methods can sometimes be inadequate, resulting in residual noise or the introduction of new artifacts. Such deficiencies are typically not captured by metrics like SI-SNR but are noticeable to human listeners. To address this, we introduce SpeechRefiner, a post-processing tool that utilizes Conditional Flow Matching (CFM) to improve the perceptual quality of speech. In this study, we benchmark SpeechRefiner against recent task-specific refinement methods and evaluate its performance within our internal processing pipeline, which integrates multiple front-end algorithms. Experiments show that SpeechRefiner exhibits strong generalization across diverse impairment sources, significantly enhancing speech perceptual quality. Audio demos can be found at https://speechrefiner.github.io/SpeechRefiner/.

eess.AS↗

arXiv2025

Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extraction

Audio-visual target speaker extraction (AV-TSE) models primarily rely on target visual cues to isolate the target speaker's voice from others. We know that humans leverage linguistic knowledge, such as syntax and semantics, to support speech perception. Inspired by this, we explore the potential of pre-trained speech-language models (PSLMs) and pre-trained language models (PLMs) as auxiliary knowledge sources for AV-TSE. In this study, we propose incorporating the linguistic constraints from PSLMs or PLMs for the AV-TSE model as additional supervision signals. Without introducing any extra computational cost during inference, the proposed approach consistently improves speech quality and intelligibility. Furthermore, we evaluate our method in multi-language settings and visual cue-impaired scenarios and show robust performance gains.

cs.SD↗

arXiv2025

Exploring Length Generalization For Transformer-based Speech Enhancement

Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for training on long speech utterances. In practical scenarios, speech enhancement models are often required to perform on noisy speech at run-time that is substantially longer than the training utterances. It remains a challenge how a Transformer-based speech enhancement model can generalize to long speech utterances. In this paper, extensive empirical studies are conducted to explore the model's length generalization ability. In particular, we conduct speech enhancement experiments on four training objectives and evaluate with five metrics. Our studies establish that positional encoding is an effective instrument to dampen the effect of utterance length on speech enhancement. We first explore several existing positional encoding methods, and the results show that relative positional encoding methods exhibit a better length generalization property than absolute positional encoding methods. Additionally, we also explore a simpler and more effective positional encoding scheme, i.e. LearnLin, that uses only one trainable parameter for each attention head to scale the real relative position between time frames, which learns the different preferences on short- or long-term dependencies of these heads. The results demonstrate that our proposal exhibits excellent length generalization ability with comparable or superior performance than other state-of-the-art positional encoding strategies.

eess.AS↗

arXiv2025

Towards Emotionally Consistent Text-Based Speech Editing: Introducing EmoCorrector and The ECD-TSE Dataset

Text-based speech editing (TSE) modifies speech using only text, eliminating re-recording. However, existing TSE methods, mainly focus on the content accuracy and acoustic consistency of synthetic speech segments, and often overlook the emotional shifts or inconsistency issues introduced by text changes. To address this issue, we propose EmoCorrector, a novel post-correction scheme for TSE. EmoCorrector leverages Retrieval-Augmented Generation (RAG) by extracting the edited text's emotional features, retrieving speech samples with matching emotions, and synthesizing speech that aligns with the desired emotion while preserving the speaker's identity and quality. To support the training and evaluation of emotional consistency modeling in TSE, we pioneer the benchmarking Emotion Correction Dataset for TSE (ECD-TSE). The prominent aspect of ECD-TSE is its inclusion of $<$text, speech$>$ paired data featuring diverse text variations and a range of emotional expressions. Subjective and objective experiments and comprehensive analysis on ECD-TSE confirm that EmoCorrector significantly enhances the expression of intended emotion while addressing emotion inconsistency limitations in current TSE methods. Code and audio examples are available at https://github.com/AI-S2-Lab/EmoCorrector.

eess.AS↗

arXiv2025

PersonaTAB: Predicting Personality Traits using Textual, Acoustic, and Behavioral Cues in Fully-Duplex Speech Dialogs

Despite significant progress in neural spoken dialog systems, personality-aware conversation agents -- capable of adapting behavior based on personalities -- remain underexplored due to the absence of personality annotations in speech datasets. We propose a pipeline that preprocesses raw audio recordings to create a dialogue dataset annotated with timestamps, response types, and emotion/sentiment labels. We employ an automatic speech recognition (ASR) system to extract transcripts and timestamps, then generate conversation-level annotations. Leveraging these annotations, we design a system that employs large language models to predict conversational personality. Human evaluators were engaged to identify conversational characteristics and assign personality labels. Our analysis demonstrates that the proposed system achieves stronger alignment with human judgments compared to existing approaches.

cs.SD↗

arXiv2025

Chain-Talker: Chain Understanding and Rendering for Empathetic Conversational Speech Synthesis

Conversational Speech Synthesis (CSS) aims to align synthesized speech with the emotional and stylistic context of user-agent interactions to achieve empathy. Current generative CSS models face interpretability limitations due to insufficient emotional perception and redundant discrete speech coding. To address the above issues, we present Chain-Talker, a three-stage framework mimicking human cognition: Emotion Understanding derives context-aware emotion descriptors from dialogue history; Semantic Understanding generates compact semantic codes via serialized prediction; and Empathetic Rendering synthesizes expressive speech by integrating both components. To support emotion modeling, we develop CSS-EmCap, an LLM-driven automated pipeline for generating precise conversational speech emotion captions. Experiments on three benchmark datasets demonstrate that Chain-Talker produces more expressive and empathetic speech than existing methods, with CSS-EmCap contributing to reliable emotion modeling. The code and demos are available at: https://github.com/AI-S2-Lab/Chain-Talker.

cs.SD↗

arXiv2025

What Is Next for LLMs? Next-Generation AI Computing Hardware Using Photonic Chips

Large language models (LLMs) are rapidly pushing the limits of contemporary computing hardware. For example, training GPT-3 has been estimated to consume around 1300 MWh of electricity, and projections suggest future models may require city-scale (gigawatt) power budgets. These demands motivate exploration of computing paradigms beyond conventional von Neumann architectures. This review surveys emerging photonic hardware optimized for next-generation generative AI computing. We discuss integrated photonic neural network architectures (e.g., Mach-Zehnder interferometer meshes, lasers, wavelength-multiplexed microring resonators) that perform ultrafast matrix operations. We also examine promising alternative neuromorphic devices, including spiking neural network circuits and hybrid spintronic-photonic synapses, which combine memory and processing. The integration of two-dimensional materials (graphene, TMDCs) into silicon photonic platforms is reviewed for tunable modulators and on-chip synaptic elements. Transformer-based LLM architectures (self-attention and feed-forward layers) are analyzed in this context, identifying strategies and challenges for mapping dynamic matrix multiplications onto these novel hardware substrates. We then dissect the mechanisms of mainstream LLMs, such as ChatGPT, DeepSeek, and LLaMA, highlighting their architectural similarities and differences. We synthesize state-of-the-art components, algorithms, and integration methods, highlighting key advances and open issues in scaling such systems to mega-sized LLM models. We find that photonic computing systems could potentially surpass electronic processors by orders of magnitude in throughput and energy efficiency, but require breakthroughs in memory, especially for long-context windows and long token sequences, and in storage of ultra-large datasets.

cs.AR↗