Plenary lecture of ICONIP 2017
Deep Neural Networks for Supervised Speech Separation
DeLiang Wang (The Ohio State University, USA)
Speech separation, or the cocktail party problem, has evaded a solution for decades in speech and audio processing. Motivated by auditory perception, I have been advocating a new formulation to this old challenge that estimates an ideal time-frequency mask (binary or ratio). This new formulation has an important implication that the speech separation problem is open to modern machine learning techniques, and deep neural networks (DNNs) are particularly well-suited for this task due to their representational capacity. I will describe recent algorithms that employ DNNs for supervised speech separation. DNN-based mask estimation elevates speech separation performance to a new level, and produces the first demonstration of substantial speech intelligibility improvements for both hearing-impaired and normal-hearing listeners in background noise. These advances represent major progress towards solving the cocktail party problem.
- Paper Submission Deadline
June 15, 2017
June 30, 2017 - Notification of Acceptance
July 31, 2017 - Final Paper Submission
August 20, 2017 - Congress Date
November 14–18, 2017
Contact Us
Address: 95 Zhongguancun East Road,
Beijing 100190, China
Email: iconip2017@foxmail.com
Fax: +86-10-8254-4799