Events Calendar

Research Activities on Speech Signal Processing in Yonsei DSP Labs

Speaker: Prof. Hong-Goo Kang , Department of Electrical and Electronic Engineering Yonsei University

Talk Title: Research Activities on Speech Signal Processing in Yonsei DSP Labs

Abstract: Speech signal processing technology, the most natural form of human communication channel, has made remarkable progress over the last 40 years. Although it is very impressive that many speech signal processing systems work very well, there still remain some challenges to be solved. For example, the accuracy of automatic speech recognition systems in adverse conditions needs to be improved to have comparable performance to human beings, and the synthesized speech generated by text-to-speech (TTS) systems needs to be more natural. This talk introduces research activities on speech signal processing group in DSP laboratory at Yonsei university. After briefly introducing the organization of research subgroups, recent research activities and their outcomes are presented. This talk emphasizes the importance of collaboration between different research subgroups having various expertises. For example, enhancement techniques are needed to improve voice communication quality for coding applications as well as to decrease the error rate of recognition systems in adverse conditions. Since hidden Markov model (HMM) and language modeling are core technologies for both speech recognition and text-to-speech (TTS), collaboration between two research subgroups is beneficial. This talk demonstrates research outcomes that our research team has achieved for last two years through tight collaboration.

Biography: Hong-Goo Kang received the B.S., M.S., and Ph.D. degrees from Yonsei University, Korea in 1989, 1991, and 1995, respectively. From 1996 to 2002, he was a senior technical staff member at AT&T Labs-Research, Florham Park, New Jersey. He is currently a Professor at Yonsei University. His research interests include speech/audio signal processing, adaptive digital filter, and human computer interface. He actively participated in international collaboration activities on making new speech/audio coding standard algorithms hosted by ITU-T and MPEG. He was an associate editor of the IEEE Transactions on Audio, Speech, and Language processing from 2005 to 2008. He served numerous conferences and program committees. He was a vice chair of technical program committee in INTERSPEECH2004 held in Jeju island, Korea. He is a technical reviewing committee member of the ICASSP and INTERSPEECH conferences. He is working on single-/multi-channel speech enhancement, universal speech/audio codec, speech/speaker recognition, and text-to-speech systems with fifteen graduate students.

Host: Prof. Shrikanth Narayanan

Location: Ronald Tutor Hall of Engineering (RTH) - 320

Audiences: Everyone Is Invited

Contact: Talyia Veal