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-55: Language Identification and Low Resource Speech Recognition

Session Type: Poster
Time: Friday, 11 June, 14:00 - 14:45
Location: Gather.Town
Virtual Session: View on Virtual Platform
Session Chair: Zhijian Ou, Tsinghua University
 
 SPE-55.1: UNSUPERVISED NEURAL ADAPTATION MODEL BASED ON OPTIMAL TRANSPORT FOR SPOKEN LANGUAGE IDENTIFICATION
         Xugang Lu; National Institute of Information and Communications Technology
         Peng Shen; National Institute of Information and Communications Technology
         Yu Tsao; Academic Sinica
         Hisashi Kawai; National Institute of Information and Communications Technology
 
 SPE-55.2: JOINT ASR AND LANGUAGE IDENTIFICATION USING RNN-T: AN EFFICIENT APPROACH TO DYNAMIC LANGUAGE SWITCHING
         Surabhi Punjabi; Amazon
         Harish Arsikere; Amazon
         Zeynab Raeesy; Amazon
         Chander Chandak; Amazon
         Nikhil Bhave; Amazon
         Ankish Bansal; Amazon
         Markus Muller; Amazon
         Sergio Murillo; Amazon
         Ariya Rastrow; Amazon
         Andreas Stolcke; Amazon
         Jasha Droppo; Amazon
         Sri Garimella; Amazon
         Roland Maas; Amazon
         Mat Hans; Amazon
         Athanasios Mouchtaris; Amazon
         Siegfried Kunzmann; Amazon
 
 SPE-55.3: SPOKEN LANGUAGE IDENTIFICATION IN UNSEEN TARGET DOMAIN USING WITHIN-SAMPLE SIMILARITY LOSS
         Muralikrishna H; Indian Institue of Technology Mandi
         Shantanu Kapoor; Manipal Institute of Technology Manipal
         Dileep Aroor Dinesh; Indian Institue of Technology Mandi
         Padmanabhan Rajan; Indian Institue of Technology Mandi
 
 SPE-55.4: EXPLORING THE USE OF COMMON LABEL SET TO IMPROVE SPEECH RECOGNITION OF LOW RESOURCE INDIAN LANGUAGES
         Vishwas M Shetty; Indian Institute of Technology, Madras
         Srinivasan Umesh; Indian Institute of Technology, Madras
 
 SPE-55.5: PHONE DISTRIBUTION ESTIMATION FOR LOW RESOURCE LANGUAGES
         Xinjian Li; Carnegie Mellon University
         Juncheng Li; Carnegie Mellon University
         Jiali Yao; Carnegie Mellon University
         Alan Black; Carnegie Mellon University
         Florian Metze; Carnegie Mellon University
 
 SPE-55.6: HOW PHONOTACTICS AFFECT MULTILINGUAL AND ZERO-SHOT ASR PERFORMANCE
         Siyuan Feng; Delft University of Technology
         Piotr Żelasko; Johns Hopkins University
         Laureano Moro-Velázquez; Johns Hopkins University
         Ali Abavisani; University of Illinois at Urbana-Champaign
         Mark Hasegawa-Johnson; University of Illinois at Urbana-Champaign
         Odette Scharenborg; Delft University of Technology
         Najim Dehak; Johns Hopkins University