Advertisement

Field Experiment System “VoiceTra”

  • Yutaka AshikariEmail author
  • Hisashi Kawai
Chapter
Part of the SpringerBriefs in Computer Science book series (BRIEFSCOMPUTER)

Abstract

This chapter introduces “VoiceTra,” a speech-to-speech translation system which utilizes the technologies introduced in the previous chapters. VoiceTra’s client application has been released as to the public as a field experiment and has marked a total of 3,921,186 downloads and has collected as many as 178,054,211 speech utterances (as of August 31st, 2019), allowing the system to make continuous improvements. The following sections will cover the system overview, the communications protocols used between the client and server, the user interface of the client application, how the utterances are processed on the speech translation server, and finally the statistical data based on user downloads and logs.

References

  1. 1.
    Kimura, N.: Speech Translation Markup Language (STML) Version 1.00. Tech. Rep., NICT, Kyoto, Japan (2008)Google Scholar
  2. 2.
    Yasuda, K., Sumita, E., Yamamoto, S., Kikui, G., Yanagida, M.: Real-time evaluation architecture for MT using multiple backward translations. In: Proceedings of RANLP2003, pp. 518–522 (2003)Google Scholar

Copyright information

© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.System Development Office, Advanced Speech Translation Research and Development Promotion CenterNational Institute of Information and Communications TechnologyKyotoJapan
  2. 2.Advanced Speech Technology Laboratory, Advanced Speech Translation Research and Development Promotion CenterNational Institute of Information and Communications TechnologyKyotoJapan

Personalised recommendations