Zobrazeno 1 - 10
of 143
pro vyhledávání: '"Xunying Liu"'
Autor:
Cai Wingfield, Chao Zhang, Barry Devereux, Elisabeth Fonteneau, Andrew Thwaites, Xunying Liu, Phil Woodland, William Marslen-Wilson, Li Su
Publikováno v:
Frontiers in Computational Neuroscience, Vol 16 (2022)
IntroductionIn recent years, machines powered by deep learning have achieved near-human levels of performance in speech recognition. The fields of artificial intelligence and cognitive neuroscience have finally reached a similar level of performance,
Externí odkaz:
https://doaj.org/article/9ee534075fed4546b6a09d781297bd19
Autor:
Cai Wingfield, Li Su, Xunying Liu, Chao Zhang, Phil Woodland, Andrew Thwaites, Elisabeth Fonteneau, William D Marslen-Wilson
Publikováno v:
PLoS Computational Biology, Vol 13, Iss 9, p e1005617 (2017)
There is widespread interest in the relationship between the neurobiological systems supporting human cognition and emerging computational systems capable of emulating these capacities. Human speech comprehension, poorly understood as a neurobiologic
Externí odkaz:
https://doaj.org/article/1fb7775ce9714964adeb462d5f480eae
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Autor:
Jiajun Deng, Xurong Xie, Tianzi Wang, Mingyu Cui, Boyang Xue, Zengrui Jin, Guinan Li, Shujie Hu, Xunying Liu
Speaker adaptation techniques provide a powerful solution to customise automatic speech recognition (ASR) systems for individual users. Practical application of unsupervised model-based speaker adaptation techniques to data intensive end-to-end ASR s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7c61b5ff35232a4cb2155430c10e5d01
Publikováno v:
Interspeech 2022.
Autor:
Tianzi Wang, Jiajun DENG, Mengzhe Geng, Zi Ye, Shoukang Hu, Yi Wang, Mingyu Cui, Zengrui Jin, Xunying Liu, Helen Meng
Publikováno v:
Interspeech 2022.
State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when given limited
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4e81cce4f3abe05d6ee6d07ab58402af
http://arxiv.org/abs/2208.13259
http://arxiv.org/abs/2208.13259
Early diagnosis of Alzheimer's disease (AD) is crucial in facilitating preventive care and delay progression. Speech based automatic AD screening systems provide a non-intrusive and more scalable alternative to other clinical screening techniques. Sc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ec107574e2e2aae0010d245e46408dfe
http://arxiv.org/abs/2206.13758
http://arxiv.org/abs/2206.13758
Publikováno v:
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).