Multilingual Speech-to-Speech Translation System: VoiceTra

Author

Matsuda, Shodai ; Xinhui Hu ; Shiga, Yoshinori ; Kashioka, Hideki ; Hori, Chiori ; Yasuda, Kazuhiro ; Okuma, Hideo ; Uchiyama, Masaru ; Sumita, Eiichiro ; Kawai, Hiroyuki ; Nakamura, Shigenari

Author_Institution

Nat. Inst. of Inf. & Commun. Technol., Universal Commun. Res. Inst., Kyoto, Japan

Volume

2

fYear

2013

fDate

3-6 June 2013

Firstpage

229

Lastpage

233

Abstract

This study presents an overview of VoiceTra, which was developed by NICT and released as the world´s first network-based multilingual speech-to-speech translation system for smartphones, and describes in detail its multilingual speech recognition, its multilingual translation, and its multilingual speech synthesis in regards to field experiments. We show the effects of system updates using the data collected from field experiments to improve our acoustic and language models.

Keywords

language translation; natural language processing; smart phones; speech recognition; speech synthesis; NICT; VoiceTra; acoustic models; language models; multilingual speech recognition; multilingual speech synthesis; network-based multilingual speech-to-speech translation system; smartphones; Acoustics; Adaptation models; Hidden Markov models; Speech; Speech recognition; Speech synthesis;

fLanguage

English

Publisher

ieee

Conference_Titel

Mobile Data Management (MDM), 2013 IEEE 14th International Conference on

Conference_Location

Milan

Print_ISBN

978-1-4673-6068-5

Type

conf

DOI

10.1109/MDM.2013.99

Filename

6569095