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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
The value set for when statistical machine translation (SMT) is processed with central processing units (CPUs) only and when neural machine translation (NMT) is processed with CPUs and general-purpose graphics processing units (GPGPUs) combined.
References
Kimura, N.: Speech Translation Markup Language (STML) Version 1.00. Tech. Rep., NICT, Kyoto, Japan (2008)
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)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Ashikari, Y., Kawai, H. (2020). Field Experiment System “VoiceTra”. In: Kidawara, Y., Sumita, E., Kawai, H. (eds) Speech-to-Speech Translation. SpringerBriefs in Computer Science. Springer, Singapore. https://doi.org/10.1007/978-981-15-0595-9_5
Download citation
DOI: https://doi.org/10.1007/978-981-15-0595-9_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-0594-2
Online ISBN: 978-981-15-0595-9
eBook Packages: Computer ScienceComputer Science (R0)