SPE-8.5
Integrating multiple ASR systems into NLP backend with attention fusion
Takatomo Kano, Atsunori Ogawa, Marc Delcroix, NTT Corporation, Japan; Shinji Watanabe, Language Technologies Institute, Carnegie Mellon University, United States of America
Session:
Machine Translation for Spoken and Written Language
Track:
Speech and Language Processing
Location:
Gather Area E
Presentation Time:
Sun, 8 May, 21:00 - 21:45 China Time (UTC +8)
Sun, 8 May, 13:00 - 13:45 UTC
Sun, 8 May, 13:00 - 13:45 UTC
Session Chair:
Jan Niehues, Maastricht University
Session SPE-8
SPE-8.1: CPT: CROSS-MODAL PREFIX-TUNING FOR SPEECH-TO-TEXT TRANSLATION
Yukun Ma, Trung Hieu Nguyen, Bin Ma, Alibaba Group, Singapore
SPE-8.2: TACKLING DATA SCARCITY IN SPEECH TRANSLATION USING ZERO-SHOT MULTILINGUAL MACHINE TRANSLATION TECHNIQUES
Tu Anh Dinh, Danni Liu, Jan Niehues, Maastricht University, Netherlands
SPE-8.3: IMPROVING END-TO-END SPEECH TRANSLATION MODEL WITH BERT-BASED CONTEXTUAL INFORMATION
Jeong-Uk Bang, Min-Kyu Lee, Seung Yun, Sang-Hun Kim, Electronics and Telecommunications Research Institute (ETRI), Korea, Republic of
SPE-8.4: Context-Adaptive Document-Level Neural Machine Translation
Linlin Zhang, Zhejiang University, China; Zhirui Zhang, Boxing Chen, Weihua Luo, Luo Si, Alibaba DAMO Academy, China
SPE-8.5: Integrating multiple ASR systems into NLP backend with attention fusion
Takatomo Kano, Atsunori Ogawa, Marc Delcroix, NTT Corporation, Japan; Shinji Watanabe, Language Technologies Institute, Carnegie Mellon University, United States of America
SPE-8.6: ISOMETRIC MT: NEURAL MACHINE TRANSLATION FOR AUTOMATIC DUBBING
Surafel Lakew, Yogesh Virkar, Prashant Mathur, Marcello Federico, Amazon AI, United States of America