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

HLT-1: Language Modeling 1: Fusion and Training for End-to-End ASR

Session Type: Poster
Time: Tuesday, 8 June, 13:00 - 13:45
Location: Gather.Town
 
HLT-1.1: IMPROVED NEURAL LANGUAGE MODEL FUSION FOR STREAMING RECURRENT NEURAL NETWORK TRANSDUCER
         Suyoun Kim; Facebook
         Yuan Shangguan; Facebook
         Jay Mahadeokar; Facebook
         Antoine Bruguier; Facebook
         Christian Fuegen; Facebook
         Michael Seltzer; Facebook
         Duc Le; Facebook
 
HLT-1.2: INTERNAL LANGUAGE MODEL TRAINING FOR DOMAIN-ADAPTIVE END-TO-END SPEECH RECOGNITION
         Zhong Meng; Microsoft Corporation
         Naoyuki Kanda; Microsoft Corporation
         Yashesh Gaur; Microsoft Corporation
         Sarangarajan Parthasarathy; Microsoft Corporation
         Eric Sun; Microsoft Corporation
         Liang Lu; Microsoft Corporation
         Xie Chen; Microsoft Corporation
         Jinyu Li; Microsoft Corporation
         Yifan Gong; Microsoft Corporation
 
HLT-1.3: SPEECH RECOGNITION BY SIMPLY FINE-TUNING BERT
         Wen-Chin Huang; Nagoya University
         Chia-Hua Wu; Academia Sinica
         Shang-Bao Luo; Academia Sinica
         Kuan-Yu Chen; National Taiwan University of Science and Technology
         Hsin-Min Wang; Academia Sinica
         Tomoki Toda; Nagoya University
 
HLT-1.4: PERSONALIZATION STRATEGIES FOR END-TO-END SPEECH RECOGNITION SYSTEMS
         Aditya Gourav; Amazon
         Linda Liu; Amazon
         Ankur Gandhe; Amazon
         Yile Gu; Amazon
         Guitang Lan; Amazon
         Xiangyang Huang; Amazon
         Shashank Kalmane; Amazon
         Gautam Tiwari; Amazon
         Denis Filimonov; Amazon
         Ariya Rastrow; Amazon
         Andreas Stolcke; Amazon
         Ivan Bulyko; Amazon
 
HLT-1.5: IMPROVING ENTITY RECALL IN AUTOMATIC SPEECH RECOGNITION WITH NEURAL EMBEDDINGS
         Christopher Li; Google
         Pat Rondon; Google
         Diamantino Caseiro; Google
         Leonid Velikovich; Google
         Xavier Velez; Google
         Petar Aleksic; Google
 
HLT-1.6: ADAPTABLE MULTI-DOMAIN LANGUAGE MODEL FOR TRANSFORMER ASR
         Taewoo Lee; Samsung Electronics
         Min-Joong Lee; Samsung Electronics
         Tae Gyoon Kang; Samsung Electronics
         Seokyeoung Jung; Samsung Electronics
         Minseok Kwon; Samsung Electronics
         Yeona Hong; Samsung Electronics
         Jungin Lee; Samsung Electronics
         Kyoung-Gu Woo; Samsung Electronics
         Ho-Gyeong Kim; Samsung Electronics
         Jiseung Jeong; Samsung Electronics
         Jihyun Lee; Samsung Electronics
         Hosik Lee; Samsung Electronics
         Young Sang Choi; Samsung Electronics