Zobrazeno 1 - 10
of 381
pro vyhledávání: '"Huang, KaiXun"'
Pre-trained multilingual speech foundation models, like Whisper, have shown impressive performance across different languages. However, adapting these models to new or specific languages is computationally extensive and faces catastrophic forgetting
Externí odkaz:
http://arxiv.org/abs/2408.10680
Open-vocabulary keyword spotting (KWS), which allows users to customize keywords, has attracted increasingly more interest. However, existing methods based on acoustic models and post-processing train the acoustic model with ASR training criteria to
Externí odkaz:
http://arxiv.org/abs/2312.09760
The attention-based deep contextual biasing method has been demonstrated to effectively improve the recognition performance of end-to-end automatic speech recognition (ASR) systems on given contextual phrases. However, unlike shallow fusion methods t
Externí odkaz:
http://arxiv.org/abs/2310.04657
Multilingual automatic speech recognition (ASR) systems have garnered attention for their potential to extend language coverage globally. While self-supervised learning (SSL) models, like MMS, have demonstrated their effectiveness in multilingual ASR
Externí odkaz:
http://arxiv.org/abs/2309.16937
Autor:
Xu, Tianyi, Yang, Zhanheng, Huang, Kaixun, Guo, Pengcheng, Zhang, Ao, Li, Biao, Chen, Changru, Li, Chao, Xie, Lei
By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words with high
Externí odkaz:
http://arxiv.org/abs/2306.00804
Contextual information plays a crucial role in speech recognition technologies and incorporating it into the end-to-end speech recognition models has drawn immense interest recently. However, previous deep bias methods lacked explicit supervision for
Externí odkaz:
http://arxiv.org/abs/2305.12493
Autor:
Zhang, Ao, Yu, Fan, Huang, Kaixun, Xie, Lei, Wang, Longbiao, Chng, Eng Siong, Bu, Hui, Zhang, Binbin, Chen, Wei, Xu, Xin
This paper summarizes the outcomes from the ISCSLP 2022 Intelligent Cockpit Speech Recognition Challenge (ICSRC). We first address the necessity of the challenge and then introduce the associated dataset collected from a new-energy vehicle (NEV) cove
Externí odkaz:
http://arxiv.org/abs/2211.01585
Autor:
Zhai, Zhihao a, b, c, Huang, Zuoyu a, c, Huang, Kaixun c, d, Zhong, Yuanqiang a, c, You, Hengxing a, c, Tao, Enxiang c, d, Yang, Yunfeng a, c, ⁎
Publikováno v:
In International Immunopharmacology 27 January 2025 146
Autor:
Liu, Xiaohuan a, 1, Su, Jiehua b, 1, Zhang, Jieli b, Li, Zhonggui b, Huang, Kaixun b, Lin, Danyu b, Tao, Enxiang a, b, ⁎
Publikováno v:
In Behavioural Brain Research 5 March 2025 480
Autor:
Wang, Xing, Li, Caina, Huan, Yi, Cao, Hui, Sun, Sujuan, Lei, Lei, Liu, Quan, Liu, Shuainan, Ji, Wenming, Huang, Kaixun, Shen, Zhufang, Zhou, Jun
Publikováno v:
In Chemico-Biological Interactions 1 April 2021 338