Zobrazeno 1 - 10
of 273
pro vyhledávání: '"LI Shengqiang"'
Autor:
Song, Xingchen, Xing, Mengtao, Ma, Changwei, Li, Shengqiang, Wu, Di, Zhang, Binbin, Pan, Fuping, Zhou, Dinghao, Zhang, Yuekai, Lei, Shun, Peng, Zhendong, Wu, Zhiyong
It is well known that LLM-based systems are data-hungry. Recent LLM-based TTS works typically employ complex data processing pipelines to obtain high-quality training data. These sophisticated pipelines require excellent models at each stage (e.g., s
Externí odkaz:
http://arxiv.org/abs/2412.08237
Autor:
SUN Yana, LIU Jianling, LIANG Guangzhong, LI Shengqiang, LI Longyu, ZHENG Mei, YANG Yong, KE Hui
Publikováno v:
Zhongguo shipin weisheng zazhi, Vol 33, Iss 05, Pp 548-552 (2021)
ObjectiveTo investigate the epidemiological characteristics and drug resistance of foodborne diseases in Jinnan District by monitoring and drug resistance analysis of foodborne diseases from 2018 to 2020, so as to provide basis for prevention and con
Externí odkaz:
https://doaj.org/article/408b453672fe43bf9df9b9ed6b397080
Publikováno v:
E3S Web of Conferences, Vol 375, p 03009 (2023)
Hydroxyl radical (·OH) can rapidly react with biological macromolecules, organic and inorganic substances on account of its strong oxidizing property, so it is widely used in sewage treatment, chemiluminescence analysis, biological macromolecule mod
Externí odkaz:
https://doaj.org/article/d3b3238703bb4d16ac9bb448bd516b91
This study describes our system for Task 1 Single-speaker Visual Speech Recognition (VSR) fixed track in the Chinese Continuous Visual Speech Recognition Challenge (CNVSRC) 2023. Specifically, we use intermediate connectionist temporal classification
Externí odkaz:
http://arxiv.org/abs/2312.07254
Autor:
Liang, Chengdong, Zhang, Xiao-Lei, Zhang, BinBin, Wu, Di, Li, Shengqiang, Song, Xingchen, Peng, Zhendong, Pan, Fuping
Recently, the unified streaming and non-streaming two-pass (U2/U2++) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy and latency. In this paper, we present fast-U2++, an enhanced version
Externí odkaz:
http://arxiv.org/abs/2211.00941
Publikováno v:
Science and Technology of Nuclear Installations, Vol 2015 (2015)
Externí odkaz:
https://doaj.org/article/150af396812044f1ac677e13d6ddd1db
Publikováno v:
In International Immunopharmacology 5 December 2024 142 Part B
Transformer-based end-to-end speech recognition models have received considerable attention in recent years due to their high training speed and ability to model a long-range global context. Position embedding in the transformer architecture is indis
Externí odkaz:
http://arxiv.org/abs/2107.05907
Deep neural networks provide effective solutions to small-footprint keyword spotting (KWS). However, if training data is limited, it remains challenging to achieve robust and highly accurate KWS in real-world scenarios where unseen sounds that are ou
Externí odkaz:
http://arxiv.org/abs/2107.05859
Autor:
Zou, Yurong, Wu, Shukun, Xu, Xingli, Tan, Xiaoqiu, Yang, Shuang, Chen, Tangting, Zhang, Jiong, Li, Shengqiang, Li, Wei, Wang, Fang
Publikováno v:
In International Immunopharmacology 30 May 2024 133