Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Chen Mengzhe"'
Autor:
Xue, Hongfei, Liang, Yuhao, Mu, Bingshen, Zhang, Shiliang, Chen, Mengzhe, Chen, Qian, Xie, Lei
This study focuses on emotion-sensitive spoken dialogue in human-machine speech interaction. With the advancement of Large Language Models (LLMs), dialogue systems can handle multimodal data, including audio. Recent models have enhanced the understan
Externí odkaz:
http://arxiv.org/abs/2401.00475
Autor:
Gao, Zhifu, Li, Zerui, Wang, Jiaming, Luo, Haoneng, Shi, Xian, Chen, Mengzhe, Li, Yabin, Zuo, Lingyun, Du, Zhihao, Xiao, Zhangyu, Zhang, Shiliang
This paper introduces FunASR, an open-source speech recognition toolkit designed to bridge the gap between academic research and industrial applications. FunASR offers models trained on large-scale industrial corpora and the ability to deploy them in
Externí odkaz:
http://arxiv.org/abs/2305.11013
Publikováno v:
Proc. Interspeech 2021
Punctuation prediction for automatic speech recognition (ASR) output transcripts plays a crucial role for improving the readability of the ASR transcripts and for improving the performance of downstream natural language processing applications. Howev
Externí odkaz:
http://arxiv.org/abs/2104.10339
With the increased applications of automatic speech recognition (ASR) in recent years, it is essential to automatically insert punctuation marks and remove disfluencies in transcripts, to improve the readability of the transcripts as well as the perf
Externí odkaz:
http://arxiv.org/abs/2003.01309
Publikováno v:
IEICE Transactions on Information and Systems. :2554-2557
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9798bfa98f38c726addfa645f2a7e8e4
https://doi.org/10.1587/transinf.2016sll0004
https://doi.org/10.1587/transinf.2016sll0004
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
IIH-MSP
In current DNN/HMM hybrid systems, the DNN models are trained by the 1-of-V targets which are obtained by the Viterbi-based forced-alignment. The states are viewed as unrelated and isolated. In fact, some phonemes are acoustically similar. Especially
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::991e9816f01b9a65f7e123fad984364f
https://doi.org/10.1109/iih-msp.2014.153
https://doi.org/10.1109/iih-msp.2014.153
Publikováno v:
CIS
This paper presents our recent work on the development of a real world voice retrieval system, which automatically updates language models for a specific domain with the latest web data. Two of the main difficult issues in handling this system are ta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a57e36da416061c03dfde6fce4604a54
https://doi.org/10.1109/cis.2013.28
https://doi.org/10.1109/cis.2013.28
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
2014 Tenth International Conference on Intelligent Information Hiding & Multimedia Signal Processing; 2014, p590-593, 4p