ICASSP 2006 - May 15-19, 2006 - Toulouse, France

Technical Program

Paper Detail

Paper:SS-13.1
Session:Speech Translation for Cross-Lingual Communication
Time:Friday, May 19, 16:30 - 16:50
Presentation: Special Session Lecture
Topic: Special Sessions: Speech translation for cross-lingual communication
Title: IBM MASTOR: MULTILINGUAL AUTOMATIC SPEECH-TO-SPEECH TRANSLATOR
Authors: Yuqing Gao, Bowen Zhou, Liang Gu, Ruhi Sarikaya, Hong-Kwang Kuo, A.-V. I. Rosti, Mohamed A. Afify, Weizhong Zhu, IBM T. J. Watson Research Center, United States
Abstract: In this paper, we describe the IBM MASTOR systems which handle spontaneous free-form speech-to-speech translation on both laptop and hand-held PDAs. Challenges include speech recognition and machine translation in adverse environments, lack of data and linguistic resources for under-studied languages, and the need to rapidly develop capabilities for new languages. Importantly, the code and models must fit within the limited memory and computational resources of hand-held devices. We describe our approaches, experience, and success in building working free-form S2S systems that can handle two language pairs (including a low-resource language).



IEEESignal Processing Society

©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012