SPE-40: Speech Recognition 14: Acoustic Modeling 2 |
Session Type: Poster |
Time: Thursday, 10 June, 15:30 - 16:15 |
Location: Gather.Town |
Virtual Session: View on Virtual Platform |
Session Chair: Xiaodong Cui, IBM |
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 |