93 citations · 230 across the 26 of their papers we have counts for
27 papers
CIViC: Evidence Gates for Audio-Conditioned Visual Prediction on Proxy Tasks
Mengzhe Geng, Max W. Y. Lam, Yuewen Cao +4
Removing audio can shift a visual predictor's output without showing whether the task uses the intended audio information. We introduce Conditional Input and Visual Interpretation…
Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask
Tianzi Wang, Xurong Xie, Zengrui Jin +9
Automatic speech recognition (ASR) systems often rely on autoregressive (AR) Transformer decoder architectures, which limit efficient inference parallelization due to their sequent…
One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model
Zhaoqing Li, Haoning Xu, Tianzi Wang +7
We propose a novel one-pass multiple ASR systems joint compression and quantization approach using an all-in-one neural model. A single compression cycle allows multiple nested sys…
Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask
Tianzi Wang, Xurong Xie, Zhaoqing Li +9
This paper proposes a novel non-autoregressive (NAR) block-based Attention Mask Decoder (AMD) that flexibly balances performance-efficiency trade-offs for Conformer ASR systems. AM…
Hyper-parameter Adaptation of Conformer ASR Systems for Elderly and Dysarthric Speech Recognition
Tianzi Wang, Shoukang Hu, Jiajun Deng +5
Automatic recognition of disordered and elderly speech remains highly challenging tasks to date due to data scarcity. Parameter fine-tuning is often used to exploit the large quant…
Exploiting prompt learning with pre-trained language models for Alzheimer's Disease detection
Yi Wang, Jiajun Deng, Tianzi Wang +4
Early diagnosis of Alzheimer's disease (AD) is crucial in facilitating preventive care and to delay further progression. Speech based automatic AD screening systems provide a non-i…
Bayesian Neural Network Language Modeling for Speech Recognition
Boyang Xue, Shoukang Hu, Junhao Xu +3
State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. Th…
Conformer Based Elderly Speech Recognition System for Alzheimer's Disease Detection
Tianzi Wang, Jiajun Deng, Mengzhe Geng +7
Early diagnosis of Alzheimer's disease (AD) is crucial in facilitating preventive care to delay further progression. This paper presents the development of a state-of-the-art Confo…
Towards Green ASR: Lossless 4-bit Quantization of a Hybrid TDNN System on the 300-hr Switchboard Corpus
Junhao Xu, Shoukang Hu, Xunying Liu +1
State of the art time automatic speech recognition (ASR) systems are becoming increasingly complex and expensive for practical applications. This paper presents the development of…
Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems
Mingyu Cui, Jiajun Deng, Shoukang Hu +7
Fundamental modelling differences between hybrid and end-to-end (E2E) automatic speech recognition (ASR) systems create large diversity and complementarity among them. This paper i…
Exploring linguistic feature and model combination for speech recognition based automatic AD detection
Yi Wang, Tianzi Wang, Zi Ye +5
Early diagnosis of Alzheimer's disease (AD) is crucial in facilitating preventive care and delay progression. Speech based automatic AD screening systems provide a non-intrusive an…
Neural Architecture Search for Speech Emotion Recognition
Xixin Wu, Shoukang Hu, Zhiyong Wu +2
Deep neural networks have brought significant advancements to speech emotion recognition (SER). However, the architecture design in SER is mainly based on expert knowledge and empi…
Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition
Shujie Hu, Shansong Liu, Xurong Xie +6
Articulatory features are inherently invariant to acoustic signal distortion and have been successfully incorporated into automatic speech recognition (ASR) systems for normal spee…
Recent Progress in the CUHK Dysarthric Speech Recognition System
Shansong Liu, Mengzhe Geng, Shoukang Hu +5
Despite the rapid progress of automatic speech recognition (ASR) technologies in the past few decades, recognition of disordered speech remains a highly challenging task to date. D…
Investigation of Data Augmentation Techniques for Disordered Speech Recognition
Mengzhe Geng, Xurong Xie, Shansong Liu +4
Disordered speech recognition is a highly challenging task. The underlying neuro-motor conditions of people with speech disorders, often compounded with co-occurring physical disab…
Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition
Mengzhe Geng, Shansong Liu, Jianwei Yu +6
Automatic recognition of disordered speech remains a highly challenging task to date. Sources of variability commonly found in normal speech including accent, age or gender, when f…
Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks
Shoukang Hu, Xurong Xie, Mingyu Cui +6
State-of-the-art automatic speech recognition (ASR) system development is data and computation intensive. The optimal design of deep neural networks (DNNs) for these systems often…
Mixed Precision of Quantization of Transformer Language Models for Speech Recognition
Junhao Xu, Shoukang Hu, Jianwei Yu +2
State-of-the-art neural language models represented by Transformers are becoming increasingly complex and expensive for practical applications. Low-bit deep neural network quantiza…
Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition
Junhao Xu, Jianwei Yu, Shoukang Hu +2
State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive…
Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers
Junhao Xu, Xie Chen, Shoukang Hu +3
The high memory consumption and computational costs of Recurrent neural network language models (RNNLMs) limit their wider application on resource constrained devices. In recent ye…
Bayesian Transformer Language Models for Speech Recognition
Boyang Xue, Jianwei Yu, Junhao Xu +6
State-of-the-art neural language models (LMs) represented by Transformers are highly complex. Their use of fixed, deterministic parameter estimates fail to account for model uncert…
Bayesian Learning of LF-MMI Trained Time Delay Neural Networks for Speech Recognition
Shoukang Hu, Xurong Xie, Shansong Liu +5
Discriminative training techniques define state-of-the-art performance for automatic speech recognition systems. However, they are inherently prone to overfitting, leading to poor…
Audio-visual Multi-channel Integration and Recognition of Overlapped Speech
Jianwei Yu, Shi-Xiong Zhang, Bo Wu +6
Automatic speech recognition (ASR) technologies have been significantly advanced in the past few decades. However, recognition of overlapped speech remains a highly challenging tas…
Understanding the wiring evolution in differentiable neural architecture search
Sirui Xie, Shoukang Hu, Xinjiang Wang +4
Controversy exists on whether differentiable neural architecture search methods discover wiring topology effectively. To understand how wiring topology evolves, we study the underl…