5 citations · 9 across the 11 of their papers we have counts for
11 papers
Streaming Speech-to-Text Translation with a SpeechLLM
Titouan Parcollet, Shucong Zhang, Xianrui Zheng +1
Normally, a system that translates speech into text consists of separate modules for speech recognition and text-to-text translation. Combining those tasks into a SpeechLLM promise…
Adaptive Federated Fine-Tuning of Self-Supervised Speech Representations
Xin Guo, Chunrui Zhao, Hong Jia +4
Integrating Federated Learning (FL) with self-supervised learning (SSL) enables privacy-preserving fine-tuning for speech tasks. However, federated environments exhibit significant…
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…
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…
Conditional Diffusion Model for Target Speaker Extraction
Theodor Nguyen, Guangzhi Sun, Xianrui Zheng +2
We propose DiffSpEx, a generative target speaker extraction method based on score-based generative modelling through stochastic differential equations. DiffSpEx deploys a continuou…
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 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…
Tandem Multitask Training of Speaker Diarisation and Speech Recognition for Meeting Transcription
Xianrui Zheng, Chao Zhang, Philip C. Woodland
Self-supervised-learning-based pre-trained models for speech data, such as Wav2Vec 2.0 (W2V2), have become the backbone of many speech tasks. In this paper, to achieve speaker diar…
Multi-turn RNN-T for streaming recognition of multi-party speech
Ilya Sklyar, Anna Piunova, Xianrui Zheng +1
Automatic speech recognition (ASR) of single channel far-field recordings with an unknown number of speakers is traditionally tackled by cascaded modules. Recent research shows tha…
Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition
Xianrui Zheng, Chao Zhang, Philip C. Woodland
Language models (LMs) pre-trained on massive amounts of text, in particular bidirectional encoder representations from Transformers (BERT), generative pre-training (GPT), and GPT-2…
Using Synthetic Audio to Improve The Recognition of Out-Of-Vocabulary Words in End-To-End ASR Systems
Xianrui Zheng, Yulan Liu, Deniz Gunceler +1
Today, many state-of-the-art automatic speech recognition (ASR) systems apply all-neural models that map audio to word sequences trained end-to-end along one global optimisation cr…