基本信息
浏览量:428
职业迁徙
个人简介
Lead a team of about 30 research scientists and engineers focused on novel speech recognition algorithms and machine learning to support all Google speech recognition products and services. Google speech recognition services now process several billions of queries a week. The team I manage is focused on improving the quality of those transcriptions by novel modeling as well as making use of the large stream of data that comes into our systems. There is a large effort in streaming, online recogntion to support mobile services like Voicesearch. Another focus is on multi-channel, farfield speech recognition to support the @Home smart speaker product. In addition, there is an effort on offline speech processing focusing on automatic closed captioning for YouTube and voicemail among others. For all these efforts, my team pushes up accuracy by developing innovative solutions based on advanced machine learning techiques, most recently focusing on end-to-end modeling (https://research.googleblog.com/2017/12/improving-end-to-end-models-for-speech.html). The output of the team is large in both publications as well as engineering, producing systems that are directly used in production.
研究兴趣
论文共 94 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
arXiv (Cornell University) (2022)
引用0浏览0引用
0
0
arXiv (Cornell University) (2021)
引用0浏览0引用
0
0
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn