Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Shuaijiang Zhao"'
Autor:
Yanguang Xu, Jianwei Sun, Yang Han, Shuaijiang Zhao, Chaoyang Mei, Tingwei Guo, Shuran Zhou, Chuandong Xie, Wei Zou, Xiangang Li
Publikováno v:
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::502e272179a547833478e5de0bd2b214
https://doi.org/10.1109/icassp43922.2022.9746762
https://doi.org/10.1109/icassp43922.2022.9746762
Autor:
Yujun Wang, Wei Zou, Guoguo Chen, Shuaijiang Zhao, Guan-Bo Wang, Mingjie Jin, Yongqing Wang, Wei-Qiang Zhang, Jiayu Du, Shuzhou Chai, Daniel Povey, Zhiyong Yan, Jan Trmal, Shinji Watanabe, Xuchen Yao, Sanjeev Khudanpur, Zhao You, Dan Su, Junbo Zhang, Chao Weng, Xiangang Li
This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and unsupervi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ac0c3ecc57cd5952693b5ab446d686f2
Autor:
Shuaijiang Zhao, Jianwei Sun, Hengxin Yin, Xiaoning Lei, Xi Zhao, Zhiyuan Tang, Xiangang Li, Wei Zou, Wei Wang
End-to-end models have gradually become the preferred option for automatic speech recognition (ASR) applications. During the training of end-to-end ASR, data augmentation is a quite effective technique for regularizing the neural networks. This paper
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9eedbcd82b60e1153a7943278dade3a4
Autor:
Dongwei Jiang, Wubo Li, Kun Han, Tingwei Guo, Wei Zou, Ruixiong Zhang, Xiangang Li, Cheng Gong, Cheng Wen, Shuaijiang Zhao, Ne Luo
Publikováno v:
ICASSP
This paper introduces a new open-sourced Mandarin speech corpus, called DiDiSpeech. It consists of about 800 hours of speech data at 48kHz sampling rate from 6000 speakers and the corresponding texts. All speech data in the corpus is recorded in quie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d3f1c677a8abaf18bfb2ca8aa11f6f09
http://arxiv.org/abs/2010.09275
http://arxiv.org/abs/2010.09275
Publikováno v:
ISCSLP
Many of the current state-of-the-art Mandarin Large Vocabulary Continuous Speech Recognition (LVCSR) Systems are built either with a hybrid of Deep Neural Network (DNN) and Hidden Markov Models (HMM) or with Neural Network model trained with Connecti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cbf47df59784cef2b3c725f6d64c9fd5
https://doi.org/10.1109/iscslp.2018.8706686
https://doi.org/10.1109/iscslp.2018.8706686
Publikováno v:
ISCSLP
End-to-end speech recognition has become increasingly popular in Mandarin speech recognition and achieved delightful performance. Mandarin is a tonal language which is different from English and requires special treatment for the acoustic modeling un
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d64df0c7d0946ba39e40171aaa924ba
https://doi.org/10.1109/iscslp.2018.8706661
https://doi.org/10.1109/iscslp.2018.8706661
Publikováno v:
Polymers and Polymer Composites. 18:411-416
The aim of the work was to study the structure and thermal property of co-polyamide (CPA)/clay nanocomposites. Two nanocomposites, based on two co-polyamides (CPA) and organic-clay, were successfully prepared by melting extrusions in a twin-screw ext
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8aee97f71955c0744fd51950f3ee1ff
https://doi.org/10.1177/096739111001800801
https://doi.org/10.1177/096739111001800801
Publikováno v:
Polymers & Polymer Composites; 2010, Vol. 18 Issue 8, p411-416, 6p, 1 Black and White Photograph, 1 Diagram, 4 Graphs