Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Kong, Yuxiang"'
Speech has emerged as a widely embraced user interface across diverse applications. However, for individuals with dysarthria, the inherent variability in their speech poses significant challenges. This paper presents an end-to-end Pretrain-based Dual
Externí odkaz:
http://arxiv.org/abs/2409.10076
Autor:
Guo, Liyong, Yang, Xiaoyu, Wang, Quandong, Kong, Yuxiang, Yao, Zengwei, Cui, Fan, Kuang, Fangjun, Kang, Wei, Lin, Long, Luo, Mingshuang, Zelasko, Piotr, Povey, Daniel
Knowledge distillation(KD) is a common approach to improve model performance in automatic speech recognition (ASR), where a student model is trained to imitate the output behaviour of a teacher model. However, traditional KD methods suffer from teach
Externí odkaz:
http://arxiv.org/abs/2211.00508
With the increasing demand for audio communication and online conference, ensuring the robustness of Acoustic Echo Cancellation (AEC) under the complicated acoustic scenario including noise, reverberation and nonlinear distortion has become a top iss
Externí odkaz:
http://arxiv.org/abs/2106.07577
Autor:
Fu, Yihui, Cheng, Luyao, Lv, Shubo, Jv, Yukai, Kong, Yuxiang, Chen, Zhuo, Hu, Yanxin, Xie, Lei, Wu, Jian, Bu, Hui, Xu, Xin, Du, Jun, Chen, Jingdong
In this paper, we present AISHELL-4, a sizable real-recorded Mandarin speech dataset collected by 8-channel circular microphone array for speech processing in conference scenario. The dataset consists of 211 recorded meeting sessions, each containing
Externí odkaz:
http://arxiv.org/abs/2104.03603
Autor:
Fu, Rong, Kong, Yuxiang, Wang, Guangming, Zhang, Zihao, Zhao, Jinsheng, Qu, Konggang, Xiong, Qingchuan, Zhao, Xiaofei, Tao, Shuo, Li, Lu
Publikováno v:
In Applied Catalysis B: Environment and Energy March 2025 362
The front-end module in multi-channel automatic speech recognition (ASR) systems mainly use microphone array techniques to produce enhanced signals in noisy conditions with reverberation and echos. Recently, neural network (NN) based front-end has sh
Externí odkaz:
http://arxiv.org/abs/2011.09081
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Guo, Liyong, Yang, Xiaoyu, Wang, Quandong, Kong, Yuxiang, Yao, Zengwei, Cui, Fan, Kuang, Fangjun, Kang, Wei, Lin, Long, Luo, Mingshuang, Zelasko, Piotr, Povey, Daniel
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Knowledge distillation(KD) is a common approach to improve model performance in automatic speech recognition (ASR), where a student model is trained to imitate the output behaviour of a teacher model. However, traditional KD methods suffer from teach
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a0d0728f74059eb8da3d228579ab5f1a
https://doi.org/10.1109/icassp49357.2023.10095268
https://doi.org/10.1109/icassp49357.2023.10095268