Zobrazeno 1 - 10 of 41 pro vyhledávání: '"Chongjia Ni"'
1
Preventing Early Endpointing for Online Automatic Speech Recognition
Autor: Shafiq Joty, Yingzhu Zhao, Cheung-Chi Leung, Eng Siong Chng, Bin Ma, Chongjia Ni
Publikováno v: ICASSP
With the recent development of end-to-end models in speech recognition, there have been more interests in adapting these models for online speech recognition. However, using end-to-end models for online speech recognition is known to suffer from an e
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0157bb4a16a85dc76fd042f39082b947
https://doi.org/10.1109/icassp39728.2021.9413613
Zobrazit plný text záznamu
5
Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning
Autor: Chongjia Ni, Haihua Xu, Van Tung Pham, Yerbolat Khassanov, Zhiping Zeng, Eng Siong Chng, Bin Ma
Publikováno v: ISCSLP
In this work, we study leveraging extra text data to improve low-resource end-to-end ASR under cross-lingual transfer learning setting. To this end, we extend our prior work [1], and propose a hybrid Transformer-LSTM based architecture. This architec
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::48803f448350bddd18797ae66fab9efd
http://arxiv.org/abs/2005.10407
Zobrazit plný text záznamu
7
Independent language modeling architecture for end-to-end ASR
Autor: Eng Siong Chng, Haizhou Li, Zhiping Zeng, Van Tung Pham, Bin Ma, Yerbolat Khassanov, Haihua Xu, Chongjia Ni
Publikováno v: ICASSP
The attention-based end-to-end (E2E) automatic speech recognition (ASR) architecture allows for joint optimization of acoustic and language models within a single network. However, in a vanilla E2E ASR architecture, the decoder sub-network (subnet),
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0197ab43ada5420ebcc26dce65d4773a
http://arxiv.org/abs/1912.00863
Zobrazit plný text záznamu
9
Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data
Autor: Haihua Xu, Van Tung Pham, Bin Ma, Eng Siong Chng, Yerbolat Khassanov, Zhiping Zeng, Chongjia Ni
Publikováno v: INTERSPEECH
The lack of code-switch training data is one of the major concerns in the development of end-to-end code-switching automatic speech recognition (ASR) models. In this work, we propose a method to train an improved end-to-end code-switching ASR using o
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6989083dfa54f99b01b0f1facc5adc4b
http://arxiv.org/abs/1904.03802
Zobrazit plný text záznamu
10
A Keyword-Aware Language Modeling Approach to Spoken Keyword Search
Autor: Chin-Hui Lee, Nancy F. Chen, I-Fan Chen, Chongjia Ni, Boon Pang Lim
Publikováno v: Journal of Signal Processing Systems. 82:197-206
A keyword-sensitive language modeling framework for spoken keyword search (KWS) is proposed to combine the advantages of conventional keyword-filler based and large vocabulary continuous speech recognition (LVCSR) based KWS systems. The proposed fram
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::4b7e7d1037a9589d54a2716eea6e6066
https://doi.org/10.1007/s11265-015-0998-0
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje