IEEE ICASSP 2022

2022 IEEE International Conference on Acoustics, Speech and Signal Processing

7-13 May 2022
  • Virtual (all paper presentations)
22-27 May 2022
  • Main Venue: Marina Bay Sands Expo & Convention Center, Singapore
27-28 October 2022
  • Satellite Venue: Crowne Plaza Shenzhen Longgang City Centre, Shenzhen, China

ICASSP 2022
AUD-23: Speech Separation II
Wed, 11 May, 22:00 - 22:45 China Time (UTC +8)
Wed, 11 May, 14:00 - 14:45 UTC
Location: Gather Area K
Session Chair: Keisuke Kinoshita, NTT Corporation
Track: Audio and Acoustic Signal Processing

AUD-23.1: SKIM: SKIPPING MEMORY LSTM FOR LOW-LATENCY REAL-TIME CONTINUOUS SPEECH SEPARATION
Chenda Li, Yanmin Qian, Shanghai Jiao Tong University, China; Lei Yang, Weiqin Wang, Samsung Research China - Beijing, China

AUD-23.2: ADAPTING SPEECH SEPARATION TO REAL-WORLD MEETINGS USING MIXTURE INVARIANT TRAINING
Aswin Sivaraman, Indiana University, United States of America; Scott Wisdom, Hakan Erdogan, John R. Hershey, Google Research, United States of America

AUD-23.3: QUANTIFYING DISCRIMINABILITY BETWEEN NMF BASES
Eisuke Konno, Daisuke Saito, Nobuaki Minematsu, The University of Tokyo, Japan

AUD-23.4: LOCATION-BASED TRAINING FOR MULTI-CHANNEL TALKER-INDEPENDENT SPEAKER SEPARATION
Hassan Taherian, Ke Tan, DeLiang Wang, The Ohio State University, United States of America

AUD-23.5: SDR — MEDIUM RARE WITH FAST COMPUTATIONS
Robin Scheibler, LINE Corporation, Japan

AUD-23.6: AttentionPIT: Soft permutation invariant training for audio source separation with attention mechanism
HIrokazu Kameoka, Shogo Seki, Li Li, Chihiro Watanabe, Nippon Telegraph and Telephone Corporation, Japan