CloudASR: A Web Platform for Automatic Speech Recognition

Speaker:
Ondřej Klejch
Abstract:
We present a web platform for Automatic Speech Recognition built on top of Kaldi toolkit, which supports both batch and on-line recognition and has an annotation interface for transcription of the gathered speech recordings. By providing such service we want to offer the developers an easy way to use voice control in their applications. Also we want to collect and publish new speech data for further research.  I will also mention how we deploy and run the CloudASR platform in a robust and scalable way using technology similar to how Google and Facebook run their software platforms. Demo of the platform is available at demo.cloudasr.com.
Length:
00:32:49
Date:
16/03/2015
views:

Images:
Preview of 1.jpg
Image 1.jpg
Preview of 2.jpg
Image 2.jpg
Preview of 3.jpg
Image 3.jpg
Attachments: (video, slides, etc.)
46 MB
173 downloads
519 MB
168 downloads
75 MB
173 downloads
101 MB
170 downloads
191 MB
179 downloads
618 downloads