IEEE ICASSP 2024 || Seoul, Korea || 14-19 April 2024

SLP-L26: Machine translation for spoken and written language I

Fri, 19 Apr, 13:10 - 15:10 (UTC +9)

Location: Room 201

Session Type: Lecture

Session Co-Chairs: Kai Yu, Shanghai Jiao Tong University and Peter Bell, University of Edinburgh

Track: Speech and Language Processing

Fri, 19 Apr, 13:10 - 13:30 (UTC +9)

SLP-L26.1: M2BART: MULTILINGUAL AND MULTIMODAL ENCODER-DECODER PRE-TRAINING FOR ANY-TO-ANY MACHINE TRANSLATION

Peng-Jen Chen, Bowen Shi, Kelvin Niu, Ann Lee, Wei-Ning Hsu, Meta, United States of America

Fri, 19 Apr, 13:30 - 13:50 (UTC +9)

SLP-L26.2: COLLD: CONTRASTIVE LAYER-TO-LAYER DISTILLATION FOR COMPRESSING MULTILINGUAL PRE-TRAINED SPEECH ENCODERS

Heng-Jui Chang, Massachusetts Institute of Technology, United States of America; Ning Dong, Ruslan Mavlyutov, Sravya Popuri, Yu-An Chung, Meta Platforms, Inc., United States of America

Fri, 19 Apr, 13:50 - 14:10 (UTC +9)

SLP-L26.3: END-TO-END SPEECH TRANSLATION WITH MUTUAL KNOWLEDGE DISTILLATION

Hao Wang, Beijing OPPO Telecommunications Corp., Ltd., China; Zhengshan Xue, Beijing OPPO Telecommunications Corp., Ltd.; College of Intelligence and Computing, Tianjin University, China; Yikun Lei, Deyi Xiong, College of Intelligence and Computing, Tianjin University, China

Fri, 19 Apr, 14:10 - 14:30 (UTC +9)

SLP-L26.1: M2BART: MULTILINGUAL AND MULTIMODAL ENCODER-DECODER PRE-TRAINING FOR ANY-TO-ANY MACHINE TRANSLATION

SLP-L26.2: COLLD: CONTRASTIVE LAYER-TO-LAYER DISTILLATION FOR COMPRESSING MULTILINGUAL PRE-TRAINED SPEECH ENCODERS

SLP-L26.3: END-TO-END SPEECH TRANSLATION WITH MUTUAL KNOWLEDGE DISTILLATION

SLP-L26.4: MEMORY-AUGMENTED SPEECH-TO-TEXT TRANSLATION WITH MULTI-SCALE CONTEXT TRANSLATION STRATEGY

SLP-L26.5: DIARIST: STREAMING SPEECH TRANSLATION WITH SPEAKER DIARIZATION

SLP-L26.6: GLANCING FUTURE FOR SIMULTANEOUS MACHINE TRANSLATION