activity
20202026
most citedRecent Progress in the CUHK Dysarthric Speech Recognition System

93 citations · 215 across the 49 of their papers we have counts for

collaborators
Showing 2022Show all

14 papers · 1 filter

eess.AS2022★ 1 cited

Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition

Zengrui Jin, Xurong Xie, Mengzhe Geng +5

Automatic recognition of disordered speech remains a highly challenging task to date. The underlying neuro-motor conditions, often compounded with co-occurring physical disabilitie…

cs.CL2022★ 1 cited

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…

eess.AS2022

Confidence Score Based Conformer Speaker Adaptation for Speech Recognition

Jiajun Deng, Xurong Xie, Tianzi Wang +7

A key challenge for automatic speech recognition (ASR) systems is to model the speaker level variability. In this paper, compact speaker dependent learning hidden unit contribution…

eess.AS2022★ 38 cited

Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition

Zengrui Jin, Mengzhe Geng, Jiajun Deng +4

Despite the rapid progress of automatic speech recognition (ASR) technologies targeting normal speech, accurate recognition of dysarthric and elderly speech remains highly challeng…

eess.AS2022

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…

eess.AS2022★ 6 cited

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…