11 citations · 34 across the 18 of their papers we have counts for
18 papers
From Semantics to Readout: Mechanistic Understanding of Audio Tokens after Fine-Tuning for Temporal Audio Grounding
Yujian Ma, Jinqiu Sang, Ruizhe Li +2
Large audio-language models (LALMs) convey acoustic evidence to language decoders through native audio tokens, yet the internal roles of these tokens remain poorly understood. Usin…
Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue System
Chen Chen, Ruizhe Li, Yuchen Hu +3
Intelligent task-oriented dialogue systems (ToDs) are expected to continuously acquire new knowledge, also known as Continual Learning (CL), which is crucial to fit ever-changing u…
Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models
Yuchen Hu, Chen Chen, Chengwei Qin +3
Recent advances in large language models (LLMs) have promoted generative error correction (GER) for automatic speech recognition (ASR), which aims to predict the ground-truth trans…
It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition
Chen Chen, Ruizhe Li, Yuchen Hu +4
Recent studies have successfully shown that large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (…
GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators
Yuchen Hu, Chen Chen, Chao-Han Huck Yang +4
Recent advances in large language models (LLMs) have stepped forward the development of multilingual speech and machine translation by its reduced representation errors and incorpo…
Large Language Models are Efficient Learners of Noise-Robust Speech Recognition
Yuchen Hu, Chen Chen, Chao-Han Huck Yang +4
Recent advances in large language models (LLMs) have promoted generative error correction (GER) for automatic speech recognition (ASR), which leverages the rich linguistic knowledg…
Noise-aware Speech Enhancement using Diffusion Probabilistic Model
Yuchen Hu, Chen Chen, Ruizhe Li +2
With recent advances of diffusion model, generative speech enhancement (SE) has attracted a surge of research interest due to its great potential for unseen testing noises. However…
MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition
Yuchen Hu, Chen Chen, Ruizhe Li +2
Audio-visual speech recognition (AVSR) attracts a surge of research interest recently by leveraging multimodal signals to understand human speech. Mainstream approaches addressing…
Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition
Yuchen Hu, Ruizhe Li, Chen Chen +3
Audio-visual speech recognition (AVSR) provides a promising solution to ameliorate the noise-robustness of audio-only speech recognition with visual information. However, most exis…
Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition
Yuchen Hu, Ruizhe Li, Chen Chen +3
Audio-visual speech recognition (AVSR) research has gained a great success recently by improving the noise-robustness of audio-only automatic speech recognition (ASR) with noise-in…
Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition
Yuchen Hu, Chen Chen, Ruizhe Li +2
Speech enhancement (SE) is proved effective in reducing noise from noisy speech signals for downstream automatic speech recognition (ASR), where multi-task learning strategy is emp…
On the Latent Holes of VAEs for Text Generation
Ruizhe Li, Xutan Peng, Chenghua Lin
In this paper, we provide the first focused study on the discontinuities (aka. holes) in the latent space of Variational Auto-Encoders (VAEs), a phenomenon which has been shown to…
Affective Decoding for Empathetic Response Generation
Chengkun Zeng, Guanyi Chen, Chenghua Lin +2
Understanding speaker's feelings and producing appropriate responses with emotion connection is a key communicative skill for empathetic dialogue systems. In this paper, we propose…
Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation
Ruizhe Li, Xiao Li, Guanyi Chen +1
The Variational Autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences. However, an issue known as posterior collapse (or KL loss…
DGST: a Dual-Generator Network for Text Style Transfer
Xiao Li, Guanyi Chen, Chenghua Lin +1
We propose DGST, a novel and simple Dual-Generator network architecture for text Style Transfer. Our model employs two generators only, and does not rely on any discriminators or p…
A Stable Variational Autoencoder for Text Modelling
Ruizhe Li, Xiao Li, Chenghua Lin +2
Variational Autoencoder (VAE) is a powerful method for learning representations of high-dimensional data. However, VAEs can suffer from an issue known as latent variable collapse (…
Latent Space Factorisation and Manipulation via Matrix Subspace Projection
Xiao Li, Chenghua Lin, Ruizhe Li +2
We tackle the problem disentangling the latent space of an autoencoder in order to separate labelled attribute information from other characteristic information. This then allows u…
A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification
Ruizhe Li, Chenghua Lin, Matthew Collinson +2
Recognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition. In this paper, we propose a dual-atten…