2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

SPE-43: Speech Recognition 15: Robust Speech Recognition 1

Session Type: Poster
Time: Thursday, 10 June, 16:30 - 17:15
Location: Gather.Town
Session Chair: Abdelrahman Mohamed, Facebook AI Research (FAIR)
 
SPE-43.1: A CLOSER LOOK AT AUDIO-VISUAL MULTI-PERSON SPEECH RECOGNITION AND ACTIVE SPEAKER SELECTION
         Otavio Braga; Google, Inc.
         Olivier Siohan; Google, Inc.
 
SPE-43.2: GENERALIZED KNOWLEDGE DISTILLATION FROM AN ENSEMBLE OF SPECIALIZED TEACHERS LEVERAGING UNSUPERVISED NEURAL CLUSTERING
         Takashi Fukuda; IBM Research AI
         Gakuto Kurata; IBM Research AI
 
SPE-43.3: MULTISTREAM CNN FOR ROBUST ACOUSTIC MODELING
         Kyu Han; ASAPP
         Jing Pan; ASAPP
         Venkata Tadala; Sensory
         Tao Ma; ASAPP
         Dan Povey; Xiaomi
 
SPE-43.4: IMPROVED ROBUSTNESS TO DISFLUENCIES IN RNN-TRANSDUCER BASED SPEECH RECOGNITION
         Valentin Mendelev; Amazon
         Tina Raissi; RWTH Aachen University
         Guglielmo Camporese; University of Padova
         Manuel Giollo; Amazon
 
SPE-43.5: REPRESENTATION LEARNING FOR SPEECH RECOGNITION USING FEEDBACK BASED RELEVANCE WEIGHTING
         Purvi Agrawal; Indian Institute of Science
         Sriram Ganapathy; Indian Institute of Science
 
SPE-43.6: TOWARDS DATA SELECTION ON TTS DATA FOR CHILDREN'S SPEECH RECOGNITION
         Wei Wang; Shanghai Jiao Tong University
         Zhikai Zhou; Shanghai Jiao Tong University
         Yizhou Lu; Shanghai Jiao Tong University
         Hongji Wang; Shanghai Jiao Tong University
         Chenpeng Du; Shanghai Jiao Tong University
         Yanmin Qian; Shanghai Jiao Tong University