no code implementations • 31 Mar 2024 • Shujie Hu, Long Zhou, Shujie Liu, Sanyuan Chen, Hongkun Hao, Jing Pan, Xunying Liu, Jinyu Li, Sunit Sivasankaran, Linquan Liu, Furu Wei
In this work, we introduce WavLLM, a robust and adaptive speech large language model with dual encoders, and a prompt-aware LoRA weight adapter, optimized by a two-stage curriculum learning approach.
no code implementations • 30 Dec 2023 • Hongkun Hao, Long Zhou, Shujie Liu, Jinyu Li, Shujie Hu, Rui Wang, Furu Wei
In this paper, we conduct a comprehensive empirical exploration of boosting LLMs with the ability to generate speech, by combining pre-trained LLM LLaMA/OPT and text-to-speech synthesis model VALL-E. We compare three integration methods between LLMs and speech synthesis models, including directly fine-tuned LLMs, superposed layers of LLMs and VALL-E, and coupled LLMs and VALL-E using LLMs as a powerful text encoder.
no code implementations • 14 Dec 2023 • Zengrui Jin, Xurong Xie, Tianzi Wang, Mengzhe Geng, Jiajun Deng, Guinan Li, Shujie Hu, Xunying Liu
Automatic recognition of disordered speech remains a highly challenging task to date due to data scarcity.
no code implementations • 6 Jul 2023 • Guinan Li, Jiajun Deng, Mengzhe Geng, Zengrui Jin, Tianzi Wang, Shujie Hu, Mingyu Cui, Helen Meng, Xunying Liu
Accurate recognition of cocktail party speech containing overlapping speakers, noise and reverberation remains a highly challenging task to date.
no code implementations • 26 Jun 2023 • Jiajun Deng, Guinan Li, Xurong Xie, Zengrui Jin, Mingyu Cui, Tianzi Wang, Shujie Hu, Mengzhe Geng, Xunying Liu
Rich sources of variability in natural speech present significant challenges to current data intensive speech recognition technologies.
no code implementations • 24 May 2023 • Xiaoyang Song, Akshat Gupta, Kiyan Mohebbizadeh, Shujie Hu, Anant Singh
In this paper, we show that we do not yet have the right tools to measure personality in language models.
no code implementations • 18 May 2023 • Mengzhe Geng, Zengrui Jin, Tianzi Wang, Shujie Hu, Jiajun Deng, Mingyu Cui, Guinan Li, Jianwei Yu, Xurong Xie, Xunying Liu
A key challenge in dysarthric speech recognition is the speaker-level diversity attributed to both speaker-identity associated factors such as gender, and speech impairment severity.
no code implementations • 28 Feb 2023 • Shujie Hu, Xurong Xie, Zengrui Jin, Mengzhe Geng, Yi Wang, Mingyu Cui, Jiajun Deng, Xunying Liu, Helen Meng
Experiments conducted on the UASpeech dysarthric and DementiaBank Pitt elderly speech corpora suggest TDNN and Conformer ASR systems integrated domain adapted wav2vec2. 0 models consistently outperform the standalone wav2vec2. 0 models by statistically significant WER reductions of 8. 22% and 3. 43% absolute (26. 71% and 15. 88% relative) on the two tasks respectively.
1 code implementation • 15 Feb 2023 • Jiajun Deng, Xurong Xie, Tianzi Wang, Mingyu Cui, Boyang Xue, Zengrui Jin, Guinan Li, Shujie Hu, Xunying Liu
Practical application of unsupervised model-based speaker adaptation techniques to data intensive end-to-end ASR systems is hindered by the scarcity of speaker-level data and performance sensitivity to transcription errors.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 3 Nov 2022 • Zengrui Jin, Xurong Xie, Mengzhe Geng, Tianzi Wang, Shujie Hu, Jiajun Deng, Guinan Li, Xunying Liu
After LHUC speaker adaptation, the best system using VAE-GAN based augmentation produced an overall WER of 27. 78% on the UASpeech test set of 16 dysarthric speakers, and the lowest published WER of 57. 31% on the subset of speakers with "Very Low" intelligibility.
no code implementations • 23 Jun 2022 • Mingyu Cui, Jiajun Deng, Shoukang Hu, Xurong Xie, Tianzi Wang, Shujie Hu, Mengzhe Geng, Boyang Xue, Xunying Liu, Helen Meng
Fundamental modelling differences between hybrid and end-to-end (E2E) automatic speech recognition (ASR) systems create large diversity and complementarity among them.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 15 Jun 2022 • Shujie Hu, Xurong Xie, Mengzhe Geng, Mingyu Cui, Jiajun Deng, Guinan Li, Tianzi Wang, Xunying Liu, Helen Meng
Articulatory features are inherently invariant to acoustic signal distortion and have been successfully incorporated into automatic speech recognition (ASR) systems designed for normal speech.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 13 May 2022 • Zengrui Jin, Mengzhe Geng, Jiajun Deng, Tianzi Wang, Shujie Hu, Guinan Li, Xunying Liu
Despite the rapid progress of automatic speech recognition (ASR) technologies targeting normal speech, accurate recognition of dysarthric and elderly speech remains highly challenging tasks to date.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 28 Mar 2022 • Mengzhe Geng, Xurong Xie, Rongfeng Su, Jianwei Yu, Zengrui Jin, Tianzi Wang, Shujie Hu, Zi Ye, Helen Meng, Xunying Liu
Accurate recognition of dysarthric and elderly speech remain challenging tasks to date.
no code implementations • 19 Mar 2022 • Shujie Hu, Shansong Liu, Xurong Xie, Mengzhe Geng, Tianzi Wang, Shoukang Hu, Mingyu Cui, Xunying Liu, Helen Meng
Articulatory features are inherently invariant to acoustic signal distortion and have been successfully incorporated into automatic speech recognition (ASR) systems for normal speech.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 21 Feb 2022 • Mengzhe Geng, Xurong Xie, Zi Ye, Tianzi Wang, Guinan Li, Shujie Hu, Xunying Liu, Helen Meng
Motivated by the spectro-temporal level differences between dysarthric, elderly and normal speech that systematically manifest in articulatory imprecision, decreased volume and clarity, slower speaking rates and increased dysfluencies, novel spectrotemporal subspace basis deep embedding features derived using SVD speech spectrum decomposition are proposed in this paper to facilitate auxiliary feature based speaker adaptation of state-of-the-art hybrid DNN/TDNN and end-to-end Conformer speech recognition systems.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • NeurIPS Workshop AI4Scien 2021 • Yuanqi Du, Shiyu Wang, Xiaojie Guo, Hengning Cao, Shujie Hu, Junji Jiang, Aishwarya Varala, Abhinav Angirekula, Liang Zhao
Graph generation, which learns from known graphs and discovers novel graphs, has great potential in numerous research topics like drug design and mobility synthesis and is one of the fastest-growing domains recently due to its promise for discovering new knowledge.