Presentation | 2019-03-15 [Poster Presentation] Simultaneous Japanese Flexible-Keyword Detection and Speaker Recognition for Low-Resource Devices Hiroshi Fujimura, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose a novel method of simultaneous keyword detection and speaker recognition for low resource devices in this study. Some applications controlled by voice commands for home appliances and smart speakers increase gradually. For example, an air conditioner turns on when you say "Turn on air-con" to the air conditioner. If a speaker is specified from the voice command, the range of the application will increase. It can adjust the setting of temperature to the speaker after the air conditioner turns on. However, much calculation cost is not allowed for devices of home appliances. Furthermore, a target of many speaker recognition methods is for utterances that have more than 2 seconds. Therefore, we propose a low-cost method of simultaneous keyword detection and speaker recognition for short keyword-voices without keyword-voice database for training. We compared the proposed method with the i-vector method. The result when using a conventional i-vector method is 74.2% for 10 keywords that uttered by 50 speakers. In contrast, the result by the proposed method is 88.9%. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | keyword detection / low resource / speaker identification / speaker recognition |
Paper # | EA2018-157,SIP2018-163,SP2018-119 |
Date of Issue | 2019-03-07 (EA, SIP, SP) |
Conference Information | |
Committee | EA / SIP / SP |
---|---|
Conference Date | 2019/3/14(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | i+Land nagasaki (Nagasaki-shi) |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Engineering/Electro Acoustics, Signal Processing, Speech, and Related Topics |
Chair | Suehiro Shimauchi(Kanazawa Inst. of Tech.) / Shogo Muramatsu(Niigata Univ.) / Yoichi Yamashita(Ritsumeikan Univ.) |
Vice Chair | Kenichi Furuya(Oita Univ.) / Kanji Watanabe(Akita Pref. Univ.) / Naoyuki Aikawa(TUS) / Kazunori Hayashi(Osaka City Univ) / Akinobu Ri(Nagoya Inst. of Tech.) |
Secretary | Kenichi Furuya(Shizuoka Inst. of Science and Tech.) / Kanji Watanabe(NHK) / Naoyuki Aikawa(Takushoku Univ.) / Kazunori Hayashi(Hiroshima Univ.) / Akinobu Ri(Kyoto Univ.) |
Assistant | Keisuke Imoto(Ritsumeikan Univ.) / Daisuke Morikawa(Toyama Pref Univ.) / Katsumi Konishi(Hosei Univ.) / hyihsin(Takushoku Univ.) / Tomoki Koriyama(Tokyo Inst. of Tech.) / Satoshi Kobashikawa(NTT) |
Paper Information | |
Registration To | Technical Committee on Engineering Acoustics / Technical Committee on Signal Processing / Technical Committee on Speech |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Poster Presentation] Simultaneous Japanese Flexible-Keyword Detection and Speaker Recognition for Low-Resource Devices |
Sub Title (in English) | |
Keyword(1) | keyword detection |
Keyword(2) | low resource |
Keyword(3) | speaker identification |
Keyword(4) | speaker recognition |
1st Author's Name | Hiroshi Fujimura |
1st Author's Affiliation | TOSHIBA(TOSHIBA) |
Date | 2019-03-15 |
Paper # | EA2018-157,SIP2018-163,SP2018-119 |
Volume (vol) | vol.118 |
Number (no) | EA-495,SIP-496,SP-497 |
Page | pp.pp.341-346(EA), pp.341-346(SIP), pp.341-346(SP), |
#Pages | 6 |
Date of Issue | 2019-03-07 (EA, SIP, SP) |