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-31: Speech Recognition 11: Novel Approaches

Session Type: Poster
Time: Thursday, 10 June, 13:00 - 13:45
Location: Gather.Town
Virtual Session: View on Virtual Platform
Session Chair: Jinyu Li, Microsoft
 
 SPE-31.1: MINIMUM BAYES RISK TRAINING FOR END-TO-END SPEAKER-ATTRIBUTED ASR
         Naoyuki Kanda; Microsoft
         Zhong Meng; Microsoft
         Liang Lu; Microsoft
         Yashesh Gaur; Microsoft
         Xiaofei Wang; Microsoft
         Zhuo Chen; Microsoft
         Takuya Yoshioka; Microsoft
 
 SPE-31.2: MUTUALLY-CONSTRAINED MONOTONIC MULTIHEAD ATTENTION FOR ONLINE ASR
         Jaeyun Song; Korea Advanced Institute of Science and Technology (KAIST)
         Hajin Shim; Korea Advanced Institute of Science and Technology (KAIST)
         Eunho Yang; Korea Advanced Institute of Science and Technology (KAIST)
 
 SPE-31.3: THE USE OF VOICE SOURCE FEATURES FOR SUNG SPEECH RECOGNITION
         Gerardo Roa Dabike; University of Sheffield
         Jon Barker; University of Sheffield
 
 SPE-31.4: A PARALLELIZABLE LATTICE RESCORING STRATEGY WITH NEURAL LANGUAGE MODELS
         Ke Li; Johns Hopkins University
         Daniel Povey; Xiaomi Corp.
         Sanjeev Khudanpur; Johns Hopkins University
 
 SPE-31.5: DECENTRALIZING FEATURE EXTRACTION WITH QUANTUM CONVOLUTIONAL NEURAL NETWORK FOR AUTOMATIC SPEECH RECOGNITION
         Chao-Han Huck Yang; Georgia Institute of Technology
         Jun Qi; Georgia Institute of Technology
         Pin-Yu Chen; IBM Research
         Yen-Chi Samuel Chen; Brookhaven National Laboratory
         Sabato Marco Siniscalchi; University of Enna
         Xiaoli Ma; Brookhaven National Laboratory
         Chin-Hui Lee; Georgia Institute of Technology
 
 SPE-31.6: CIF-BASED COLLABORATIVE DECODING FOR END-TO-END CONTEXTUAL SPEECH RECOGNITION
         Minglun Han; Institute of Automation, Chinese Academy of Sciences
         Linhao Dong; Institute of Automation, Chinese Academy of Sciences
         Shiyu Zhou; Institute of Automation, Chinese Academy of Sciences
         Bo Xu; Institute of Automation, Chinese Academy of Sciences