Highly technical voice recognition technologyAmiVoice®A growing number of services using
Advanced Media Corporation (Head office: Toshima-ku, Tokyo; President and CEO: Kiyoyuki Suzuki; hereinafter "Advanced Media") has announced the launch of the new "FOMA® We will begin offering a Distributed Speech Recognition (DSR)* server for the "905i Series."
Advanced Media is a company that develops voice recognition technology.AmiVoice®As a pioneer in voice recognition technology, we have been providing voice recognition solutions that improve business efficiency, mainly in the fields of medicine, parliamentary minutes, and call centers, and have been highly praised.® Following the launch of the voice recognition DSR client in the FOMA 905i series, NTT DoCoMo disclosed technical information about the DSR client.® We have begun offering a distributed voice recognition server for the "FOMA 905i Series." At the same time, we have begun offering a standalone version of the distributed voice recognition server, which has been made more compact and enables all voice recognition processing to be done within the mobile device. By using our distributed voice recognition server and standalone version of the voice recognition engine, content providers can develop games and internet searches that utilize highly accurate voice recognition technology.® Our voice recognition technology for the "905i Series" has been highly evaluated for its high technical capabilities and consulting capabilities, and has been adopted by the following company.
Ekimae Tanken Club Co., Ltd. "Quick Transfer DX Mega"
MTI Corporation "Job Shortcut Mapple" My Car Navigation (i-app®)
JORDAN Co., Ltd. "Transfer Guide NEXT"
Advanced Media, together with content providers, is developing the "FOMA® By utilizing voice recognition technology for the 905i Series, we will provide mobile phone users with even greater fun and ease of use.
*) Distributed Speech Recognition (DSR) is a method of achieving highly accurate speech recognition on mobile phones by performing acoustic analysis of speech on a mobile phone terminal, converting it into features required for speech recognition, sending the features to a server, and then carrying out the remaining speech recognition processing on the server. DSR has the following advantages: 30) Since it transmits digitalized data called features, there is no deterioration in sound quality during the transmission process, achieving highly accurate speech recognition; XNUMX) Since feature data is less than XNUMX/XNUMX the size of voice data, waiting time for data transmission and reception is short and there is no packet loss; and XNUMX) communication charges can be reduced by using data transmission and reception packets.
[Inquiries regarding this matter]
●Media relations: Public Relations, Corporate Planning Department
TEL. 03-5949-2007 FAX. 03-5958-1032
E-mail.
press@advanced-media.co.jp
●Customer: Sasaki, Solutions Division
TEL. 03-5958-1091 FAX. 03-5958-1033
E-mail.
info@advanced-media.co.jp
[Copyright/Trademark]
Copyright 2007 Advanced Media, Inc.
AmiVoice® and logo are registered trademarks of Advanced Media.
"FOMA" and "i-appli" are registered trademarks of NTT DoCoMo, Inc.
Company names and product names mentioned are registered trademarks and trademarks of their respective companies.
