Zobrazeno 1 - 10
of 268
pro vyhledávání: '"Liang, Zhenlin"'
Autor:
Xu, Junhao, Liang, Zhenlin, Liu, Yi, Hu, Yichao, Li, Jian, Zheng, Yajun, Cai, Meng, Wang, Hua
In this paper, we present MooER, a LLM-based large-scale automatic speech recognition (ASR) / automatic speech translation (AST) model of Moore Threads. A 5000h pseudo labeled dataset containing open source and self collected speech data is used for
Externí odkaz:
http://arxiv.org/abs/2408.05101
Code-switching speech recognition (CSSR) transcribes speech that switches between multiple languages or dialects within a single sentence. The main challenge in this task is that different languages often have similar pronunciations, making it diffic
Externí odkaz:
http://arxiv.org/abs/2306.05279
Autor:
Fan, Zhiyun, Liang, Zhenlin, Dong, Linhao, Liu, Yi, Zhou, Shiyu, Cai, Meng, Zhang, Jun, Ma, Zejun, Xu, Bo
In multi-talker scenarios such as meetings and conversations, speech processing systems are usually required to segment the audio and then transcribe each segmentation. These two stages are addressed separately by speaker change detection (SCD) and a
Externí odkaz:
http://arxiv.org/abs/2211.09381
Publikováno v:
In Aquacultural Engineering November 2024 107
Autor:
Kalhoro, Muhsan Ali, Chinta, Veeranjaneyulu, de Mutsert, Kim, Song, Guiting, Liu, Chunli, Tahir, Muhammad, Liang, Zhenlin
Publikováno v:
In Marine Pollution Bulletin November 2024 208
Autor:
Zheng, Yujiao, Zhang, Jiating, Xie, Wude, Zhu, Lixin, Guo, Tingting, Pan, Jiahui, Guo, Chunliu, Wang, Xu, Liang, Zhenlin, Jiang, Zhaoyang
Publikováno v:
In Ocean Engineering 1 November 2024 311 Part 1
Autor:
Lu, Yunlong, Liang, Zhenlin, Liu, Lijuan, Zhou, Yanyu, Liu, Chao, Zhao, Zhihao, Zheng, Tianpeng, Du, Qianming, Liu, Wukun
Publikováno v:
In European Journal of Medicinal Chemistry 5 September 2024 275
Autor:
Song, Minpeng, Ma, Junyang, Zhu, Lixin, Lu, Xiao, Liu, Haoming, Sun, Liyuan, Wang, Lu, Jiang, Feng, Liang, Zhenlin, Jiang, Zhaoyang
Publikováno v:
In Aquaculture 30 January 2025 595 Part 1
Publikováno v:
In Estuarine, Coastal and Shelf Science January 2025 312
Nowadays, most methods in end-to-end contextual speech recognition bias the recognition process towards contextual knowledge. Since all-neural contextual biasing methods rely on phrase-level contextual modeling and attention-based relevance modeling,
Externí odkaz:
http://arxiv.org/abs/2201.12806