Technical Program

ASMSP_L7: Audio source separation, enhancement and restoration

Session Type: Lecture
Time: Thursday, September 1, 14:00 - 15:40
Location: Baltic + Aegean
Session Chair: Stefan Goetze, University of Sheffield
 
ASMSP_L7.1: COSSD - AN END-TO-END FRAMEWORK FOR MULTI-INSTANCE SOURCE SEPARATION AND DETECTION
Shrishail Baligar, Shawn Newsam, University of California Merced, United States
 
ASMSP_L7.2: RECURRENT NEURAL NETWORK-BASED ESTIMATION AND CORRECTION OF RELATIVE TRANSFER FUNCTION FOR PRESERVING SPATIAL CUES IN SPEECH SEPARATION
Zicheng Feng, Fei Chen, Southern University of Science and Technology, China; Yu Tsao, Academia Sinica, Taiwan
 
ASMSP_L7.3: SAMPLING FREQUENCY INDEPENDENT DIALOGUE SEPARATION
Jouni Paulus, Matteo Torcoli, Fraunhofer Institute for Integrated Circuits IIS, Germany
 
ASMSP_L7.4: METRICGAN+/-: INCREASING ROBUSTNESS OF NOISE REDUCTION ON UNSEEN DATA
George Close, Thomas Hain, Stefan Goetze, University of Sheffield, United Kingdom
 
ASMSP_L7.5: A COMPUTATION-EFFICIENT NEURAL NETWORK FOR VAD USING MULTI-CHANNEL FEATURE
Runze Wang, Wei-Ping Zhu, Concordia University, Canada; Iman Moazzen, Castofly Technologies, Canada