62 citations · 264 across the 51 of their papers we have counts for
53 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…
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…
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…
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…
Handling Ambiguity in Emotion: From Out-of-Domain Detection to Distribution Estimation
Wen Wu, Bo Li, Chao Zhang +5
The subjective perception of emotion leads to inconsistent labels from human annotators. Typically, utterances lacking majority-agreed labels are excluded when training an emotion…
Parameter Efficient Finetuning for Speech Emotion Recognition and Domain Adaptation
Nineli Lashkarashvili, Wen Wu, Guangzhi Sun +1
Foundation models have shown superior performance for speech emotion recognition (SER). However, given the limited data in emotion corpora, finetuning all parameters of large pre-t…
Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition
Keqi Deng, Philip C. Woodland
Although end-to-end (E2E) automatic speech recognition (ASR) has shown state-of-the-art recognition accuracy, it tends to be implicitly biased towards the training data distributio…
Speech-based Slot Filling using Large Language Models
Guangzhi Sun, Shutong Feng, Dongcheng Jiang +3
Recently, advancements in large language models (LLMs) have shown an unprecedented ability across various language tasks. This paper investigates the potential application of LLMs…
It HAS to be Subjective: Human Annotator Simulation via Zero-shot Density Estimation
Wen Wu, Wenlin Chen, Chao Zhang +1
Human annotator simulation (HAS) serves as a cost-effective substitute for human evaluation such as data annotation and system assessment. Human perception and behaviour during hum…
Decoupled Structure for Improved Adaptability of End-to-End Models
Keqi Deng, Philip C. Woodland
Although end-to-end (E2E) trainable automatic speech recognition (ASR) has shown great success by jointly learning acoustic and linguistic information, it still suffers from the ef…
Integrating Emotion Recognition with Speech Recognition and Speaker Diarisation for Conversations
Wen Wu, Chao Zhang, Philip C. Woodland
Although automatic emotion recognition (AER) has recently drawn significant research interest, most current AER studies use manually segmented utterances, which are usually unavail…
Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Data
Guangzhi Sun, Chao Zhang, Ivan Vulić +2
Manually annotating fine-grained slot-value labels for task-oriented dialogue (ToD) systems is an expensive and time-consuming endeavour. This motivates research into slot-filling…
Label-Synchronous Neural Transducer for End-to-End ASR
Keqi Deng, Philip C. Woodland
Neural transducers provide a natural way of streaming ASR. However, they augment output sequences with blank tokens which leads to challenges for domain adaptation using text data.…
Estimating the Uncertainty in Emotion Attributes using Deep Evidential Regression
Wen Wu, Chao Zhang, Philip C. Woodland
In automatic emotion recognition (AER), labels assigned by different human annotators to the same utterance are often inconsistent due to the inherent complexity of emotion and the…
Can Contextual Biasing Remain Effective with Whisper and GPT-2?
Guangzhi Sun, Xianrui Zheng, Chao Zhang +1
End-to-end automatic speech recognition (ASR) and large language models, such as Whisper and GPT-2, have recently been scaled to use vast amounts of training data. Despite the larg…
Self-supervised representations in speech-based depression detection
Wen Wu, Chao Zhang, Philip C. Woodland
This paper proposes handling training data sparsity in speech-based automatic depression detection (SDD) using foundation models pre-trained with self-supervised learning (SSL). An…
Self-Supervised Learning-Based Source Separation for Meeting Data
Yuang Li, Xianrui Zheng, Philip C. Woodland
Source separation can improve automatic speech recognition (ASR) under multi-party meeting scenarios by extracting single-speaker signals from overlapped speech. Despite the succes…
Knowledge Distillation from Multiple Foundation Models for End-to-End Speech Recognition
Xiaoyu Yang, Qiujia Li, Chao Zhang +1
Although large foundation models pre-trained by self-supervised learning have achieved state-of-the-art performance in many tasks including automatic speech recognition (ASR), know…
Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmax
Keqi Deng, Philip C. Woodland
End-to-end (E2E) automatic speech recognition (ASR) implicitly learns the token sequence distribution of paired audio-transcript training data. However, it still suffers from domai…
Distribution-based Emotion Recognition in Conversation
Wen Wu, Chao Zhang, Philip C. Woodland
Automatic emotion recognition in conversation (ERC) is crucial for emotion-aware conversational artificial intelligence. This paper proposes a distribution-based framework that for…
Biased Self-supervised learning for ASR
Florian L. Kreyssig, Yangyang Shi, Jinxi Guo +3
Self-supervised learning via masked prediction pre-training (MPPT) has shown impressive performance on a range of speech-processing tasks. This paper proposes a method to bias self…
End-to-end Spoken Language Understanding with Tree-constrained Pointer Generator
Guangzhi Sun, Chao Zhang, Philip C. Woodland
End-to-end spoken language understanding (SLU) suffers from the long-tail word problem. This paper exploits contextual biasing, a technique to improve the speech recognition of rar…