Controlled Acquisition and Abstention in Three-Channel Score Conflicts
Multimodal decision-making
Publications
This page lists 72 publications and preprints. Each record links to its paper or PDF, with DOI and Google Scholar citation information where available. An asterisk (*) marks co-first authors.
2026
Direct comparison tests for effective evaluation of text-to-speech with a small number of listeners
V2A-DPO: Omni-Preference Optimization for Video-To-Audio Generation
Video-to-audio generation
Differentiable and Severity-invariant Discrete Tokens for Dysarthric Speech Recognition
When Does a Spoken Agent Have Enough Evidence to Act? The PACT-SLM Contract Test
Spoken agents
Text Scores Can Miss Waveform Use: A Qwen2-Audio Quantization Case Study
Multimodal audio evaluation
From Scores to Evidence: Auditable Decisions Can Improve Speech Deepfake Detection
Speech deepfake detection
VoxReason: Auditing Source-Grounded Speech Plans Before Synthesis
Spoken agents
AudioNoisePrints: Model-free audio watermarking using spatial correlation in flow matching TTS
Audio watermarking
Confidence Score Guided Incremental and Speaker Adaptive Pseudo-Labeling for Semi-Supervised Elderly Speech Recognition
Explainable and Trustworthy Speech Emotion Recognition Using Confidence Score and Reinforcement Learning Rectified Speech Emotion Descriptors
Decoding while Adapting: Zero-Shot Online Speaker Adaptation via Audio-Textual Prompts for Elderly Speech Recognition
Towards Personalized Federated Learning for Dysarthric Speech Recognition
Federated learning
Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering
Auditing Generative Audio Calls for Known-Task Audio-LLM Evaluation
Audio language model evaluation
SURE-Challenge: Evaluating Speech Evidence Before Speech-LLM Generation
Speech language model evaluation
Towards Extremely Low-Bit and Multi-Precision Conformer and Speech Foundation Model Quantization
GlossMATE: Multi-Agent Translator Explanations for Glosses
Language technology
Exploring SSL Discrete Tokens for Multilingual Automatic Speech Recognition
Multilingual speech recognition
Multi-Channel Speech Enhancement for Cocktail Party Speech Emotion Recognition
Exploring Cross-Lingual Voice Conversion Methods for Anonymizing Low-Resource Text-to-Speech
Low-resource speech synthesis
2025
A Survey of Reasoning with Foundation Models: Concepts, Methodologies, and Outlook
Homogeneous Speaker Features for on-the-Fly Dysarthric and Elderly Speaker Adaptation and Speech Recognition
Speaker adaptation
Phone-purity Guided Discrete Tokens for Dysarthric Speech Recognition
Effective and Efficient Mixed Precision Quantization of Speech Foundation Models
Towards LLM-Empowered Fine-Grained Speech Descriptors for Explainable Emotion Recognition
MOPSA: Mixture of Prompt-Experts Based Speaker Adaptation for Elderly Speech Recognition
On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition
Regularized Federated Learning for Privacy-Preserving Dysarthric and Elderly Speech Recognition
Federated learning
Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems
Speech recognition
Exploring Generative AI Techniques in Government: A Case Study
Generative AI in government
Supporting SENĆOŦEN Language Documentation Efforts with Automatic Speech Recognition
Indigenous language speech recognition
Evaluating Speech Foundation Models for Automatic Speech Recognition in the Low-Resource Kanyen’kéha Language
Indigenous language speech recognition
Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask
Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates
Speech Generation for Indigenous Language Education - ICLDC9 Talk Story
2024
Enhancing pre-trained ASR system fine-tuning for dysarthric speech recognition using adversarial data augmentation
Self-supervised asr models and features for dysarthric and elderly speech recognition
Towards automatic data augmentation for disordered speech recognition
An initial investigation of language adaptation for TTS systems under low-resource scenarios
Structured speaker-deficiency adaptation of foundation models for dysarthric and elderly speech recognition
One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model
Towards high-performance and low-latency feature-based speaker adaptation of conformer speech recognition systems
Joint Speaker Features Learning for Audio-visual Multichannel Speech Separation and Recognition
Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask
2023
Exploring self-supervised pre-trained asr models for dysarthric and elderly speech recognition
Personalized adversarial data augmentation for dysarthric and elderly speech recognition
Adversarial data augmentation using VAE-GAN for disordered speech recognition
Audio-visual end-to-end multi-channel speech separation, dereverberation and recognition
Use of speech impairment severity for dysarthric speech recognition
Dysarthric speech recognition
Exploiting cross-domain and cross-lingual ultrasound tongue imaging features for elderly and dysarthric speech recognition
Hyper-parameter adaptation of conformer ASR systems for elderly and dysarthric speech recognition
On-the-fly feature based rapid speaker adaptation for dysarthric and elderly speech recognition
Speaker adaptation
Factorised Speaker-environment Adaptive Training of Conformer Speech Recognition Systems
2022
Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition
Speaker adaptation
Neural architecture search for LF-MMI trained time delay neural networks
Bayesian neural network language modeling for speech recognition
Conformer based elderly speech recognition system for Alzheimer's disease detection
Exploiting cross domain acoustic-to-articulatory inverted features for disordered speech recognition
Confidence score based conformer speaker adaptation for speech recognition
Two-pass decoding and cross-adaptation based system combination of end-to-end conformer and hybrid tdnn asr systems
2021
Recent Progress in the CUHK Dysarthric Speech Recognition System
Dysarthric speech recognition
Adversarial Data Augmentation for Disordered Speech Recognition
Adversarial data augmentation
Development of the cuhk elderly speech recognition system for neurocognitive disorder detection using the dementiabank corpus
Bayesian transformer language models for speech recognition
Audio-visual Multi-channel Integration and Recognition of Overlapped Speech
Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition
Disordered speech assessment
Bayesian learning of LF-MMI trained time delay neural networks for speech recognition
Bayesian Parametric and Architectural Domain Adaptation of LF-MMI Trained TDNNs for Elderly and Dysarthric Speech Recognition.
2020
Investigation of Data Augmentation Techniques for Disordered Speech Recognition
Disordered speech recognition