The ATR Multilingual Speech-to-Speech Translation System

Nakamura, Satoshi; Markov, Konstantin; Nakaiwa, Hiromi; Kikui, Genichiro; Kawai, Hisashi; Jitsuhiro, Takatoshi; Zhang, Jinsong; Yamamoto, Hirotsugu; Sumita, Eiichiro; Yamamoto, Seiichi

doi:10.1109/tsa.2005.860774

Cited by 112 publications

(59 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…ATR Automatic Speech Recognition (ATRASR) (Nakamura et al, 2006) was used for phoneme recognition and connected word recognition. An acoustic model and finitestate automaton for Japanese phonemes were given, but the knowledge of words was not.…”

Section: Conditionsmentioning

confidence: 99%

Learning Physically Grounded Lexicons from Spoken Utterances

Taguchi¹,

Iwahashi²,

Funakoshi³

et al. 2012

Human Machine Interaction - Getting Closer

View full text Add to dashboard Cite

Section: Conditionsmentioning

confidence: 99%

Learning Physically Grounded Lexicons from Spoken Utterances

Taguchi¹,

Iwahashi²,

Funakoshi³

et al. 2012

Human Machine Interaction - Getting Closer

View full text Add to dashboard Cite

“…This process is also useful for deciding the threshold on the SIFT matching score. Figure 5 shows a schematic of the speech processing of the method, which uses automatic speech recognition (ASR) system called ATRASR (25). ATRASR is a hidden Markov model (HMM)-based speech recognition system, and it is used as a front-end and word/phoneme decoder.…”

Section: Maximum Plane Is Detected As Table Top Using Randomized Hougmentioning

confidence: 99%

Learning Novel Objects for Domestic Service Robots

Attamimi¹,

Nagaoka²,

Nagai³

et al. 2012

The Future of Humanoid Robots - Research and Applications

View full text Add to dashboard Cite

“…In Japan, both the Advanced Telecommunications Research Institute International (ATR) and the National Institute of Information and Communications Technology (NICT) are engaged in the research and development activities of speech translation systems [4] through field experiments by assuming actual use environments [2], [3]. Additionally, the Verbmobil project [5] in Germany conducts research on speech translation between Japanese, English, and German, and the NESPOLE!…”

Section: Introductionmentioning

confidence: 99%

Development of the “VoiceTra” Multi-Lingual Speech Translation System

Matsuda

Hayashi

Ashikari

et al. 2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis study introduces large-scale field experiments of VoiceTra, which is the world's first speech-to-speech multilingual translation application for smart phones. In the study, approximately 10 million input utterances were collected since the experiments commenced. The usage of collected data was analyzed and discussed. The study has several important contributions. First, it explains system configuration, communication protocol between clients and servers, and details of multilingual automatic speech recognition, multilingual machine translation, and multilingual speech synthesis subsystems. Second, it demonstrates the effects of mid-term system updates using collected data to improve an acoustic model, a language model, and a dictionary. Third, it analyzes system usage.

show abstract

The ATR Multilingual Speech-to-Speech Translation System

Cited by 112 publications

References 21 publications

Learning Physically Grounded Lexicons from Spoken Utterances

Learning Physically Grounded Lexicons from Spoken Utterances

Learning Novel Objects for Domestic Service Robots

Development of the “VoiceTra” Multi-Lingual Speech Translation System

Contact Info

Product

Resources

About