This event has ended. Visit the official site or create your own event on Sched.
June 25 - 27 - Beijing, China
Click Here For Information & Registration

Back To Schedule
Monday, June 25 • 16:40 - 17:20
AI Applications at DiDi: End-to-End Speech Systems - Xiangang Li, DiDi

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
At DiDi, there are around 30 million rides per day, which creates very big data for AI applications. AI is widely used to provide the best-in-class ride-sharing experience and the AI strategy of DiDi is “AI for transportation”. In this talk, the AI layout and applications will be briefly introduced. About the AI applications, this talk will focus on discussing the state-of-the-art end-to-end speech technologies and their applications at DiDi.


李先刚:滴滴语音负责人,他长期从事语音识别(Speech Recognition)、语音合成(Speech Synthesis)、说话人识别(Speaker Recognition)等方向的研究。曾参与Blizzard 2013国际语音合成比赛,搭建了当时最好的英语语音合成系统,在比赛中的各个性能衡量指标上都获得了第一。加入滴滴之前,他是某著名互联网公司的语音技术部的识别技术负责人之一,参与推动了多个端对端(end-to-end)语音系统的研发,包括DeepSpeech,DeepSpeaker等。

avatar for Xiangang Li

Xiangang Li

DIDI Voice Technology Leader (滴滴语音技术负责人)
Mr. Li Xiangang, Head of Didi Voice, has been engaging in the research of speech recognition, speech synthesis, and speaker recognition. He participated in the Blizzard 2013 International Speech Synthesis Competition and he created the best English speech synthesis system during the... Read More →

Monday June 25, 2018 16:40 - 17:20 CST