Presentation | 2019-01-24 Development of living sound and non-verbal sound real-time recognition system using imitated syllable definition against non-verbal sound Shotaro Takenouchi, Masayuki Numao, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose a real-time non-verbal sound and daily-life sound recognition system, which also reflects identificating with speech and noise. To take characteristic of non-verbal sounds into consideration, we build a recognition method in the form of extending recognition targets of in generic speech recognition method. And we implemented by using a real-time speech recognition engine, which is suitable for our proposal. In order to identificating non-verbal sound accurately, we applied imitate syllable models to non-verbal sound. As a result of 3 evaluations against our proposal, we obtained the possibility of applicating to non-verbal sound recognition by using pseudo phoneme sequence definition. And even if laughter during speech, we got the result that laughter can be detected at a rate of about 50%. However, as a result of evaluation that assumed real time recognition from continuous sound, there was the problem that detection accuracy of non-verbal sound. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Non-Velbal Sound Recognition / Life-Sound Recognition / Realtime Recognition / Imitate syllable definition / Julius |
Paper # | ICM2018-40,LOIS2018-46 |
Date of Issue | 2019-01-17 (ICM, LOIS) |
Conference Information | |
Committee | ICM / LOIS |
---|---|
Conference Date | 2019/1/24(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Practical Use of Lifelog, Office Information System, Business Management, etc. |
Chair | Kiyohito Yoshihara(KDDI Research) / Tomohiro Yamada(NTT) |
Vice Chair | Yoichi Yamashita(NTT-N) / Takumi Miyoshi(Shibaura Inst. of Tech.) / Toru Kobayashi(Nagasaki Univ.) |
Secretary | Yoichi Yamashita(KDDI Research) / Takumi Miyoshi(NTT) / Toru Kobayashi(NTT) |
Assistant | Yunchen Zhu(Hitachi) / Shinichiro Eitoku(NTT) |
Paper Information | |
Registration To | Technical Committee on Information and Communication Management / Technical Committee on Life Intelligence and Office Information Systems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Development of living sound and non-verbal sound real-time recognition system using imitated syllable definition against non-verbal sound |
Sub Title (in English) | |
Keyword(1) | Non-Velbal Sound Recognition |
Keyword(2) | Life-Sound Recognition |
Keyword(3) | Realtime Recognition |
Keyword(4) | Imitate syllable definition |
Keyword(5) | Julius |
1st Author's Name | Shotaro Takenouchi |
1st Author's Affiliation | The University of Electro-Communications(UEC) |
2nd Author's Name | Masayuki Numao |
2nd Author's Affiliation | The University of Electro-Communications(UEC) |
Date | 2019-01-24 |
Paper # | ICM2018-40,LOIS2018-46 |
Volume (vol) | vol.118 |
Number (no) | ICM-419,LOIS-420 |
Page | pp.pp.27-32(ICM), pp.27-32(LOIS), |
#Pages | 6 |
Date of Issue | 2019-01-17 (ICM, LOIS) |