Colloquium Details
Recognition, Retrieval and Content Analysis for Massive Speech Data
| Author: | Associate Professor Ji Wu Tsinghua University in Beijing, China |
|---|---|
| Date: | October 16, 2014 |
| Time: | 15:30 |
| Location: | 220 Deschutes |
Abstract
Call centers are an important way to provide information and service to users, which is very popular in the modern society. A large amount of speech data is created everyday in call centers in the fields such as telecom, insurance and financial services. All these spontaneous telephony speech signals pose a challenge to automatic speech recognition (ASR) technologies, even with significant progress in recent years. Given its large scale, it's not trivial to perform spoken document retrieval for specific topics. It is even more difficult if we try to understand the intention of the users who make those phone calls.
In this talk, I will talk about a speech content analysis platform developed at the Multimedia Signal and Intelligence Information Processing Lab at Tsinghua University for call centers in China that integrates ASR, audio indexing and spoken language understanding techniques. Quality inspection of custom service can be automatically achieved through this platform and its analysis results will be of a great help to strategy design and initiative marketing. The platform has been widely used in call centers in more than twelve provinces in China.
Biography
Ji Wu is an associate professor at the Department of Electronic Engineering, Tsinghua University, Beijing, China and currently a visiting scholar at School of Electrical and Computer Engineering, Georgia Institute of Technology. He received his B.S. and Ph.D degrees from Tsinghua University, in 1996 and 2001, respectively, both in electronic engineering.
He is heading the Multimedia Signal and Intelligence Information Processing Lab at Tsinghua University. Since 2006, he has been the director of Tsinghua-iFlyTek Joint Lab for Speech Technologies. He is also the leader of SIAC-TWG (Technical Work Group of Speech Industry Alliance of China). His research interests include speech recognition, natural language processing, pattern recognition, machine learning and data mining.