6 papers
DNCASR: End-to-End Training for Speaker-Attributed ASR
Xianrui Zheng, Chao Zhang, Philip C. Woodland
This paper introduces DNCASR, a novel end-to-end trainable system designed for joint neural speaker clustering and automatic speech recognition (ASR), enabling speaker-attributed t…
MT2KD: Towards A General-Purpose Encoder for Speech, Speaker, and Audio Events
Xiaoyu Yang, Qiujia Li, Chao Zhang +1
With the advances in deep learning, the performance of end-to-end (E2E) single-task models for speech and audio processing has been constantly improving. However, it is still chall…
An Improved Empirical Fisher Approximation for Natural Gradient Descent
Xiaodong Wu, Wenyi Yu, Chao Zhang +1
Approximate Natural Gradient Descent (NGD) methods are an important family of optimisers for deep learning models, which use approximate Fisher information matrices to pre-conditio…
SOT Triggered Neural Clustering for Speaker Attributed ASR
Xianrui Zheng, Guangzhi Sun, Chao Zhang +1
This paper introduces a novel approach to speaker-attributed ASR transcription using a neural clustering method. With a parallel processing mechanism, diarisation and ASR can be ap…
Confidence Estimation for Automatic Detection of Depression and Alzheimer's Disease Based on Clinical Interviews
Wen Wu, Chao Zhang, Philip C. Woodland
Speech-based automatic detection of Alzheimer's disease (AD) and depression has attracted increased attention. Confidence estimation is crucial for a trust-worthy automatic diagnos…
1st Place Solution to Odyssey Emotion Recognition Challenge Task1: Tackling Class Imbalance Problem
Mingjie Chen, Hezhao Zhang, Yuanchao Li +11
Speech emotion recognition is a challenging classification task with natural emotional speech, especially when the distribution of emotion types is imbalanced in the training and t…