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-40: Speech Recognition 14: Acoustic Modeling 2

Session Type: Poster
Time: Thursday, 10 June, 15:30 - 16:15
Location: Gather.Town
 
SPE-40.1: ENSEMBLE COMBINATION BETWEEN DIFFERENT TIME SEGMENTATIONS
         Jeremy Heng Meng Wong; Microsoft
         Dimitrios Dimitriadis; Microsoft
         Kenichi Kumatani; Microsoft
         Yashesh Gaur; Microsoft
         George Polovets; Microsoft
         Partha Parthasarathy; Microsoft
         Eric Sun; Microsoft
         Jinyu Li; Microsoft
         Yifan Gong; Microsoft
 
SPE-40.2: STREAMING END-TO-END SPEECH RECOGNITION WITH JOINTLY TRAINED NEURAL FEATURE ENHANCEMENT
         Chanwoo Kim; Samsung Research
         Abhinav Garg; Samsung Research
         Dhananjaya Gowda; Samsung Research
         Seongkyu Mun; Samsung Research
         Changwoo Han; Samsung Research
 
SPE-40.3: TRANSFORMER IN ACTION: A COMPARATIVE STUDY OF TRANSFORMER-BASED ACOUSTIC MODELS FOR LARGE SCALE SPEECH RECOGNITION APPLICATIONS
         Yongqiang Wang; Facebook
         Yangyang Shi; Facebook
         Frank Zhang; Facebook
         Chunyang Wu; Facebook
         Julian Chan; Facebook
         Ching-Feng Yeh; Facebook
         Alex Xiao; Facebook
 
SPE-40.4: EMFORMER: EFFICIENT MEMORY TRANSFORMER BASED ACOUSTIC MODEL FOR LOW LATENCY STREAMING SPEECH RECOGNITION
         Yangyang Shi; Facebook AI
         Yongqiang Wang; Facebook AI
         Chunyang Wu; Facebook AI
         Ching-Feng Yeh; Facebook AI
         Julian Chan; Facebook AI
         Frank Zhang; Facebook AI
         Duc Le; Facebook AI
         Mike Seltzer; Facebook AI
 
SPE-40.5: LEARNED TRANSFERABLE ARCHITECTURES CAN SURPASS HAND-DESIGNED ARCHITECTURES FOR LARGE SCALE SPEECH RECOGNITION
         Liqiang He; Tencent
         Dan Su; Tencent
         Dong Yu; Tencent
 
SPE-40.6: MULTITASK LEARNING AND JOINT OPTIMIZATION FOR TRANSFORMER-RNN-TRANSDUCER SPEECH RECOGNITION
         Jae-Jin Jeon; Kakaoenterprise
         Euisung Kim; Kakaoenterprise