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

Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICASSP 2021 Open Preview.

SPE-47: Speech Recognition 17: Speech Adaptation and Normalization

Session Type: Poster
Time: Friday, 11 June, 11:30 - 12:15
Location: Gather.Town
Virtual Session: View on Virtual Platform
Session Chair: Shinji Watanabe, Johns Hopkins University
 
 SPE-47.1: MULTIPLE-HYPOTHESIS CTC-BASED SEMI-SUPERVISED ADAPTATION OF END-TO-END SPEECH RECOGNITION
         Cong-Thanh Do; Toshiba Europe Limited
         Rama Doddipatla; Toshiba Europe Limited
         Thomas Hain; University of Sheffield
 
 SPE-47.2: VOWEL NON-VOWEL BASED SPECTRAL WARPING AND TIME SCALE MODIFICATION FOR IMPROVEMENT IN CHILDREN’S ASR
         Hemant Kathania; Aalto University
         Avinash Kumar; Nayional Institute of Technology Sikkim
         Mikko Kurimo; Aalto University
 
 SPE-47.3: EXTENDING PARROTRON: AN END-TO-END, SPEECH CONVERSION AND SPEECH RECOGNITION MODEL FOR ATYPICAL SPEECH
         Rohan Doshi; Google
         Youzheng Chen; Google
         Liyang Jiang; Google
         Xia Zhang; Google
         Fadi Biadsy; Google
         Bhuvana Ramabhadran; Google
         Fang Chu; Google
         Andrew Rosenberg; Google
         Pedro J. Moreno; Google Inc.
 
 SPE-47.4: FUNDAMENTAL FREQUENCY FEATURE NORMALIZATION AND DATA AUGMENTATION FOR CHILD SPEECH RECOGNITION
         Gary Yeung; University of California, Los Angeles
         Ruchao Fan; University of California, Los Angeles
         Abeer Alwan; University of California, Los Angeles
 
 SPE-47.5: ANALYSIS OF X-VECTORS FOR LOW-RESOURCE SPEECH RECOGNITION
         Martin Karafiat; Brno University of Technology
         Karel Vesely; Brno University of Technology
         Jan "Honza" Cernocky; Brno University of Technology
         Jan Profant; Phonexia.s.r.o.
         Jiri Nytra; Phonexia.s.r.o.
         Miroslav Hlavacek; Phonexia.s.r.o.
         Tomas Pavlicek; Phonexia.s.r.o.
 
 SPE-47.6: REFINING AUTOMATIC SPEECH RECOGNITION SYSTEM FOR OLDER ADULTS
         Liu Chen; Oregon Health and Science University
         Meysam Asgari; Oregon Health and Science University