Presentation | 2014-05-15 Cool Implementaiton of Voice Recognition System for Web Application Yuichi MAKI, Noriyoshi KAMADO, Shigeru FUJIMURA, Yushi AONO, Joji NAKAYAMA, Sumitaka SAKAUCHI, Tomohiro YAMADA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose a browser-based speech recognition system using HTML5 in a broad sense and report its performance in actual use. Our proposed method enables browsers in PCs and mobile devices to use speech recognition function by client-side JavaScript code. Unlike traditional Web applications, there is no need to install specific application or browser plug-in. The flow of processing, at first getting the streaming audio data from the microphone of the client, and the client device transmits its streaming data to the speech-recognition server by the WebSocket protocol. In consideration of the quality of mobile broadband, by using client-side JavaScript, compression for audio data is also performed, and the Voice Activity Detector(VAD) and the speech recognition decoder are implemented to the server because of the reduction of the computational cost of the client. In this paper, we explain the architecture of our proposed system and support status of browsers and devices. And we also report the audio compression performance in the client and the quality of actual use in mobile broadband. In the result, the proposed method has adequate quality as using speech recognition system. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Voice Recognition / Web Application / Web Browser / WebSocket / Media Stream / Web Audio API |
Paper # | MoNA2014-6 |
Date of Issue |
Conference Information | |
Committee | MoNA |
---|---|
Conference Date | 2014/5/8(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Mobile Network and Applications(MoNA) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Cool Implementaiton of Voice Recognition System for Web Application |
Sub Title (in English) | |
Keyword(1) | Voice Recognition |
Keyword(2) | Web Application |
Keyword(3) | Web Browser |
Keyword(4) | WebSocket |
Keyword(5) | Media Stream |
Keyword(6) | Web Audio API |
1st Author's Name | Yuichi MAKI |
1st Author's Affiliation | NTT Service Evolution Laboratories, NIPPON TELEGRAPH AND TELEPHONE CORPORATION() |
2nd Author's Name | Noriyoshi KAMADO |
2nd Author's Affiliation | NTT Media Intelligence Laboratories |
3rd Author's Name | Shigeru FUJIMURA |
3rd Author's Affiliation | NTT Service Evolution Laboratories, NIPPON TELEGRAPH AND TELEPHONE CORPORATION |
4th Author's Name | Yushi AONO |
4th Author's Affiliation | NTT Media Intelligence Laboratories |
5th Author's Name | Joji NAKAYAMA |
5th Author's Affiliation | NTT Service Evolution Laboratories, NIPPON TELEGRAPH AND TELEPHONE CORPORATION |
6th Author's Name | Sumitaka SAKAUCHI |
6th Author's Affiliation | NTT Media Intelligence Laboratories |
7th Author's Name | Tomohiro YAMADA |
7th Author's Affiliation | NTT Service Evolution Laboratories, NIPPON TELEGRAPH AND TELEPHONE CORPORATION |
Date | 2014-05-15 |
Paper # | MoNA2014-6 |
Volume (vol) | vol.114 |
Number (no) | 31 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |