b'Xunying Liu'

research

∙ 07/06/2023

Audio-visual End-to-end Multi-channel Speech Separation, Dereverberation and Recognition

Accurate recognition of cocktail party speech containing overlapping spe...

0 Guinan Li, et al. ∙

research

∙ 06/27/2023

Hyper-parameter Adaptation of Conformer ASR Systems for Elderly and Dysarthric Speech Recognition

Automatic recognition of disordered and elderly speech remains highly ch...

0 Tianzi Wang, et al. ∙

research

∙ 06/26/2023

Factorised Speaker-environment Adaptive Training of Conformer Speech Recognition Systems

Rich sources of variability in natural speech present significant challe...

0 Jiajun Deng, et al. ∙

research

∙ 06/23/2023

Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems

Current ASR systems are mainly trained and evaluated at the utterance le...

0 Mingyu Cui, et al. ∙

research

∙ 05/18/2023

Use of Speech Impairment Severity for Dysarthric Speech Recognition

A key challenge in dysarthric speech recognition is the speaker-level di...

0 Mengzhe Geng, et al. ∙

research

∙ 03/14/2023

A Hierarchical Regression Chain Framework for Affective Vocal Burst Recognition

As a common way of emotion signaling via non-linguistic vocalizations, v...

0 Jinchao Li, et al. ∙

research

∙ 03/14/2023

Leveraging Pretrained Representations with Task-related Keywords for Alzheimer's Disease Detection

With the global population aging rapidly, Alzheimer's disease (AD) is pa...

0 Jinchao Li, et al. ∙

research

∙ 02/28/2023

Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognition

Automatic recognition of disordered and elderly speech remains a highly ...

0 Shujie Hu, et al. ∙

research

∙ 02/15/2023

Confidence Score Based Speaker Adaptation of Conformer Speech Recognition Systems

Speaker adaptation techniques provide a powerful solution to customise a...

0 Jiajun Deng, et al. ∙

research

∙ 11/17/2022

Unsupervised Model-based speaker adaptation of end-to-end lattice-free MMI model for speech recognition

Modeling the speaker variability is a key challenge for automatic speech...

0 Xurong Xie, et al. ∙

research

∙ 11/03/2022

Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition

Automatic recognition of disordered speech remains a highly challenging ...

0 Zengrui Jin, et al. ∙

research

∙ 10/29/2022

Exploiting prompt learning with pre-trained language models for Alzheimer's Disease detection

Early diagnosis of Alzheimer's disease (AD) is crucial in facilitating p...

0 Yi Wang, et al. ∙

research

∙ 10/25/2022

Disentangled Speech Representation Learning for One-Shot Cross-lingual Voice Conversion Using β-VAE

We propose an unsupervised learning method to disentangle speech into co...

0 Hui Lu, et al. ∙

research

∙ 08/28/2022

Bayesian Neural Network Language Modeling for Speech Recognition

State-of-the-art neural network language models (NNLMs) represented by l...

0 Boyang Xue, et al. ∙

research

∙ 06/28/2022

Exploring linguistic feature and model combination for speech recognition based automatic AD detection

Early diagnosis of Alzheimer's disease (AD) is crucial in facilitating p...

2 Yi Wang, et al. ∙

research

∙ 06/24/2022

Confidence Score Based Conformer Speaker Adaptation for Speech Recognition

A key challenge for automatic speech recognition (ASR) systems is to mod...

0 Jiajun Deng, et al. ∙

research

∙ 06/23/2022

Conformer Based Elderly Speech Recognition System for Alzheimer's Disease Detection

Early diagnosis of Alzheimer's disease (AD) is crucial in facilitating p...

2 Tianzi Wang, et al. ∙

research

∙ 06/23/2022

Towards Green ASR: Lossless 4-bit Quantization of a Hybrid TDNN System on the 300-hr Switchboard Corpus

State of the art time automatic speech recognition (ASR) systems are bec...

0 Junhao Xu, et al. ∙

research

∙ 06/23/2022

Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems

Fundamental modelling differences between hybrid and end-to-end (E2E) au...

0 Mingyu Cui, et al. ∙

research

∙ 06/15/2022

Exploiting Cross-domain And Cross-Lingual Ultrasound Tongue Imaging Features For Elderly And Dysarthric Speech Recognition

Articulatory features are inherently invariant to acoustic signal distor...

0 Shujie Hu, et al. ∙

research

∙ 05/13/2022

Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition

Despite the rapid progress of automatic speech recognition (ASR) technol...

1 Zengrui Jin, et al. ∙

research

∙ 04/05/2022

Audio-visual multi-channel speech separation, dereverberation and recognition

Despite the rapid advance of automatic speech recognition (ASR) technolo...

0 Guinan Li, et al. ∙

research

∙ 03/31/2022

Neural Architecture Search for Speech Emotion Recognition

Deep neural networks have brought significant advancements to speech emo...

0 Xixin Wu, et al. ∙

research

∙ 03/28/2022

On-the-fly Feature Based Speaker Adaptation for Dysarthric and Elderly Speech Recognition

Automatic recognition of dysarthric and elderly speech highly challengin...

0 Mengzhe Geng, et al. ∙

research

∙ 03/19/2022

Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition

Articulatory features are inherently invariant to acoustic signal distor...

0 Shujie Hu, et al. ∙

research

∙ 02/21/2022

Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition

Despite the rapid progress of automatic speech recognition (ASR) technol...

0 Mengzhe Geng, et al. ∙

research

∙ 02/18/2022

Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation

Dysarthric speech reconstruction (DSR), which aims to improve the qualit...

0 Disong Wang, et al. ∙

research

∙ 02/18/2022

VCVTS: Multi-speaker Video-to-Speech synthesis via cross-modal knowledge transfer from voice conversion

Though significant progress has been made for speaker-dependent Video-to...

0 Disong Wang, et al. ∙

research

∙ 01/24/2022

Investigation of Deep Neural Network Acoustic Modelling Approaches for Low Resource Accented Mandarin Speech Recognition

The Mandarin Chinese language is known to be strongly influenced by a ri...

0 Xurong Xie, et al. ∙

research

∙ 01/24/2022

Variational Auto-Encoder Based Variability Encoding for Dysarthric Speech Recognition

Dysarthric speech recognition is a challenging task due to acoustic vari...

0 Xurong Xie, et al. ∙

research

∙ 01/15/2022

Recent Progress in the CUHK Dysarthric Speech Recognition System

Despite the rapid progress of automatic speech recognition (ASR) technol...

0 Shansong Liu, et al. ∙

research

∙ 01/14/2022

Investigation of Data Augmentation Techniques for Disordered Speech Recognition

Disordered speech recognition is a highly challenging task. The underlyi...

0 Mengzhe Geng, et al. ∙

research

∙ 01/14/2022

Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition

Automatic recognition of disordered speech remains a highly challenging ...

0 Mengzhe Geng, et al. ∙

research

∙ 01/08/2022

Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks

State-of-the-art automatic speech recognition (ASR) system development i...

0 Shoukang Hu, et al. ∙

research

∙ 11/29/2021

Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition

State-of-the-art language models (LMs) represented by long-short term me...

0 Junhao Xu, et al. ∙

research

∙ 11/29/2021

Mixed Precision DNN Qunatization for Overlapped Speech Separation and Recognition

Recognition of overlapped speech has been a highly challenging task to d...

0 Junhao Xu, et al. ∙

research

∙ 11/29/2021

Mixed Precision of Quantization of Transformer Language Models for Speech Recognition

State-of-the-art neural language models represented by Transformers are ...

0 Junhao Xu, et al. ∙

research

∙ 11/29/2021

Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers

The high memory consumption and computational costs of Recurrent neural ...

0 Junhao Xu, et al. ∙

research

∙ 08/02/2021

Adversarial Data Augmentation for Disordered Speech Recognition

Automatic recognition of disordered speech remains a highly challenging ...

0 Zengrui Jin, et al. ∙

research

∙ 07/19/2021

Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attacks

Existing approaches for anti-spoofing in automatic speaker verification ...

0 Xu Li, et al. ∙

research

∙ 07/07/2021

VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis

This paper describes a variational auto-encoder based non-autoregressive...

0 Hui Lu, et al. ∙

research

∙ 06/18/2021

VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion

One-shot voice conversion (VC), which performs conversion across arbitra...

0 Disong Wang, et al. ∙

research

∙ 06/18/2021

Unsupervised Domain Adaptation for Dysarthric Speech Detection via Domain Adversarial Training and Mutual Information Minimization

Dysarthric speech detection (DSD) systems aim to detect characteristics ...

0 Disong Wang, et al. ∙

research

∙ 02/09/2021

Bayesian Transformer Language Models for Speech Recognition

State-of-the-art neural language models (LMs) represented by Transformer...

0 Boyang Xue, et al. ∙

research

∙ 12/14/2020

Bayesian Learning for Deep Neural Network Adaptation

A key task for speech recognition systems is to reduce the mismatch betw...

40 Xurong Xie, et al. ∙

research

∙ 10/28/2020

Replay and Synthetic Speech Detection with Res2net Architecture

Existing approaches for replay and synthetic speech detection still lack...

0 Xu Li, et al. ∙

research

∙ 09/06/2020

Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling

This paper proposes an any-to-many location-relative, sequence-to-sequen...

0 Songxiang Liu, et al. ∙

research

∙ 09/02/2020

Understanding the wiring evolution in differentiable neural architecture search

Controversy exists on whether differentiable neural architecture search ...

18 Sirui Xie, et al. ∙

research

∙ 07/17/2020

Neural Architecture Search for Speech Recognition

Deep neural networks (DNNs) based automatic speech recognition (ASR) sys...

0 Shoukang Hu, et al. ∙

research

∙ 06/11/2020

Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification

Recently adversarial attacks on automatic speaker verification (ASV) sys...

0 Xu Li, et al. ∙

Xunying Liu

Featured Co-authors