SPE-65.2
LATTENTION: LATTICE-ATTENTION IN ASR RESCORING
Prabhat Pandey, Sergio Duarte Torres, Ali Orkan Bayer, Ankur Gandhe, Volker Leutnant, Amazon, Germany
Session:
Speech Recognition: General Topics IV
Track:
Speech and Language Processing
Location:
Gather Area C
Presentation Time:
Thu, 12 May, 20:00 - 20:45 China Time (UTC +8)
Thu, 12 May, 12:00 - 12:45 UTC
Thu, 12 May, 12:00 - 12:45 UTC
Session Chair:
Gakuto Kurata, IBM
Session SPE-65
SPE-65.1: SRU++: PIONEERING FAST RECURRENCE WITH ATTENTION FOR SPEECH RECOGNITION
Jing Pan, Tao Lei, Kwangyoun Kim, Kyu Han, ASAPP Inc, United States of America; Shinji Watanabe, Carnegie Mellon University, United States of America
SPE-65.2: LATTENTION: LATTICE-ATTENTION IN ASR RESCORING
Prabhat Pandey, Sergio Duarte Torres, Ali Orkan Bayer, Ankur Gandhe, Volker Leutnant, Amazon, Germany
SPE-65.4: LEARNING ACOUSTIC FRAME LABELING FOR PHONEME SEGMENTATION WITH REGULARIZED ATTENTION MECHANISM
Binghuai Lin, Liyuan Wang, Tencent Technology Co., Ltd, China
SPE-65.5: LISTEN, KNOW AND SPELL: KNOWLEDGE-INFUSED SUBWORD MODELING FOR IMPROVING ASR PERFORMANCE OF OOV NAMED ENTITIES
Nilaksh Das, Duen Horng Chau, Georgia Institute of Technology, United States of America; Monica Sunkara, Dhanush Bekal, Sravan Bodapati, Katrin Kirchhoff, Amazon AWS AI, United States of America
SPE-65.6: JOINT SPEECH RECOGNITION AND AUDIO CAPTIONING
Chaitanya Narisetty, Xuankai Chang, Shinji Watanabe, Carnegie Mellon University, United States of America; Emiru Tsunoo, Yosuke Kashiwagi, Michael Hentschel, Sony Group Corporation, Japan