IEEE ICASSP 2022

2022 IEEE International Conference on Acoustics, Speech and Signal Processing

7-13 May 2022
  • Virtual (all paper presentations)
22-27 May 2022
  • Main Venue: Marina Bay Sands Expo & Convention Center, Singapore
27-28 October 2022
  • Satellite Venue: Crowne Plaza Shenzhen Longgang City Centre, Shenzhen, China

ICASSP 2022
SPE-8: Machine Translation for Spoken and Written Language
Sun, 8 May, 21:00 - 21:45 China Time (UTC +8)
Sun, 8 May, 13:00 - 13:45 UTC
Location: Gather Area E
Session Chair: Jan Niehues, Maastricht University
Track: Speech and Language Processing

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