SpeechTEK.com home
Monday Tuesday Wednesday
Sunrise Discussions Customer Case Studies Speakers
Keynotes Registration SpeechTEK University
SpeechTEK 2015 - Monday, August 17, 2015
D103 – Recent Deep Neural Net Techniques for Speech Recognition
1:15 p.m - 2:00 p.m
David L Thomson, VP Speech Technology - CaptionCall

Every major speech recognition vendor has been quietly replacing Gaussian mixture models and other ASR components with deep neural nets (DNNs). This presentation explains how DNNs work and why they are so much better than previous methods. We review the latest techniques from several research centers and how much accuracy is gained with each method. The presentation includes live demos and forecasts where the technology is likely to head in the next 3 years.

Connect with
SpeechTEK 2015

Platinum Sponsors
Gold Sponsors
Corporate Sponsors
Social Media Sponsor
Tuesday Keynote Lunch Sponsor
Media Sponsors
Co-located with: