Xiangang Li
Baidu
18 Papers
63 Citations
Xiangang Li is an academic researcher from Baidu. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 5, co-authored 6 publications.
Chat about Author
Papers
•Proceedings Article
Deep speech 2: end-to-end speech recognition in English and mandarin
Dario Amodei,Sundaram Ananthanarayanan,Rishita Anubhai,Jingliang Bai,Eric Battenberg,Carl Case,Jared Casper,Bryan Catanzaro,Qiang Cheng,Guoliang Chen,Jie Chen,Jingdong Chen,Zhijie Chen,Mike Chrzanowski,Adam Coates,Greg Diamos,Ke Ding,Niandong Du,Erich Elsen,Jesse Engel,Weiwei Fang,Linxi Fan,Christopher Fougner,Liang Gao,Caixia Gong,Awni Hannun,Tony X. Han,Lappi Vaino Johannes,Bing Jiang,Cai Ju,Billy Jun,Patrick LeGresley,Libby Lin,Junjie Liu,Yang Liu,Weigao Li,Xiangang Li,Dongpeng Ma,Sharan Narang,Andrew Y. Ng,Sherjil Ozair,Yiping Peng,Ryan Prenger,Sheng Qian,Zongfeng Quan,Jonathan Raiman,Vinay Rao,Sanjeev Satheesh,David Seetapun,Shubho Sengupta,Kavya Srinet,Anuroop Sriram,Haiyuan Tang,Liliang Tang,Chong Wang,Jidong Wang,Kaifu Wang,Yi Wang,Zhijian Wang,Zhiqian Wang,Shuang Wu,Likai Wei,Bo Xiao,Wen Xie,Yan Xie,Dani Yogatama,Bin Yuan,Jun Zhan,Zhenyao Zhu +68 more
- 19 Jun 2016
TL;DR: In this article, an end-to-end deep learning approach was used to recognize either English or Mandarin Chinese speech-two vastly different languages-using HPC techniques, enabling experiments that previously took weeks to now run in days.
•Posted Content
Deep Speaker: an End-to-End Neural Speaker Embedding System
Chao Li,Ma Xiaokong,Bing Jiang,Xiangang Li,Xuewei Zhang,Xiao Liu,Ying Cao,Ajay Kannan,Zhenyao Zhu +8 more
TL;DR: Results that suggest adapting from a model trained with Mandarin can improve accuracy for English speaker recognition are presented, and it is suggested that Deep Speaker outperforms a DNN-based i-vector baseline.
609
•Proceedings Article
Gram-CTC: automatic unit selection and target decomposition for sequence labelling
Hairong Liu,Zhenyao Zhu,Xiangang Li,Sanjeev Satheesh +3 more
- 06 Aug 2017
TL;DR: The proposed Gram-CTC improves CTC in terms of both performance and efficiency on the large vocabulary speech recognition task at multiple scales of data, and can outperform the state-of-the-art on a standard speech benchmark.
•Posted Content
Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling
TL;DR: Gram-CTC as discussed by the authors proposes a new loss function to learn the best set of basic units (grams), as well as the most suitable decomposition of tar-get sequences.
27
Exploring ChatGPT's Ability to Rank Content: A Preliminary Study on Consistency with Human Preferences
TL;DR: In this article , a test set consisting of prompts is created, covering a wide range of use cases, and five models are utilized to generate corresponding responses, and ChatGPT is then instructed to rank the responses generated by these models.
25