
Special Interest Workshop
- The First Workshop of A3 Foresight Program "Ultra-realistic Acoustic Interactive Communication on Next-generation Internet"
October 17-18, 2014, UCAS-ICC, China
The first workshop was held with the following program.
Date: October 17-18, 2014
Workshop Venue: University of CAS International Convention Center, Huairou, China
October 17 (Friday)
14:00-14:30 Assemble before the DSP Building, Institute of Acoustics, Chinese Academy of Sciences
14:30-16:30 Leave for UCAS-ICC
October 18 (Saturday)
08:30-09:00 Meeting sign-in before the multi-function room, F1
09:00-09:15 Welcome
09:15-09:45 Prof. Hynek Hermansky, The Johns Hopkins University, USA
Deeply and broadly structured artificial neural nets for ASR
09:45-10:15 Prof. Haizhou Li, Institute for Infocomm Research [I2R], Singapore
Voice Conversion and Spoofing Attack on Speaker Verification
10:30-11:00 Dr. Ming Li, SYSU-CMU Joint Institute of Engineering
Robust speaker verification using simplified supervised i-vector, phonetic tokenization and articulatory features
11:00-11:30 Mr. Kang Hyun Lee, Seoul National University, Korea
Multi-channel IMM-based feature enhancement for robust speech recognition
11:30-12:00 Mr. Kang Hyun Lee, Seoul National University, Korea
DNN-based robust speech recognition using environmental estimate
14:00-14:30 Prof. Xihong Wu, Peking University
Issues and challenges in machine speech processing
14:30-15:00 Prof. Qingyang Hong, Xiamen University
A large-scale speaker detection system based on i-vector
15:00-15:30 Dr. Cheng Lu, Tsinghua University
Description of THUEE system
15:45-16:15 Dr. Jie Li, Institute of Automation, Chinese Academy of Sciences
Deep neural networks and its applications on speech recognition and speaker verification
16:15-16:45 Mr. Zeping Xiao, Beijing Institute of Technology
An Overview of BIT Speaker Identification System for IAST Evaluation
16:45-17:15 Prof, Akinori Ito, Tohoku University, Japan
Speech recognition under a real home environment using noise modeling and multiple decoding
17:15-17:45 Prof. Yonghong Yan, Institute of Acoustics, Chinese Academy of Sciences
Speech evaluation result and analysis
17:45-18:00 Closing