Presentation | 2022-03-02 [Poster Presentation] A study of shout detection for clipped speech Taito Ishida, Kazuhiro Matsuda, Takahiro Fukumori, Yoichi Yamashita, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Recently, several audio surveillance systems using shouted speech have been proposed for safety in daily life. Although only clean speech is used for training in conventional shout detection methods based on deep learning, noise in noisy environment and clipping distort target speech in real-world situations. This paper proposes a shout detection method based on deep learning with multi-condition learning for clipped speech. We compare the following three types of multi-condition learning: using only unclipped speech, using unclipped and clipped speech, and using unclipped and declipped speech. In this study, we evaluate the detection performance of clipped speech in various noisy environments. The results of experiments conducted in various noisy environments and clipping conditions demonstrate that proposed methods using multi-condition learning both better detection performance than the conventional method using only clean speech. In addition,results of experiments show that the proposed method can detect shouted speech with clipping ratios that is not included in training dataset. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | shout / deep learning / clipped speech / declipping |
Paper # | EA2021-97,SIP2021-124,SP2021-82 |
Date of Issue | 2022-02-22 (EA, SIP, SP) |
Conference Information | |
Committee | EA / SIP / SP / IPSJ-SLP |
---|---|
Conference Date | 2022/3/1(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Yoshinobu Kajikawa(Kansai Univ.) / Yukihiro Bandou(NTT) / Norihide Kitaoka(Toyohashi Univ. of Tec) / 北岡 教英(豊橋技科大) |
Vice Chair | Kenichi Furuya(Oita Univ.) / Shoichi Koyama(Univ. of Tokyo) / Toshihisa Tanaka(Tokyo Univ. Agri.&Tech.) / Takayuki Nakachi(Ryukyu Univ.) |
Secretary | Kenichi Furuya(NTT) / Shoichi Koyama(RitsumeikanUniv.) / Toshihisa Tanaka(Xiaomi) / Takayuki Nakachi(Takushoku Univ.) / (Tokyo Univ. Agri.&Tech.) / (Univ. of Tokyo) |
Assistant | Yukou Wakabayashi(Tokyo Metropolitan Univ.) / Tatsuya Komatsu(LINE) / Taichi Yoshida(UEC) / Seisuke Kyochi(Univ. of Kitakyushu) / Toru Nakashika(Univ. of Electro-Comm.) / Ryo Masumura(NTT) |
Paper Information | |
Registration To | Technical Committee on Engineering Acoustics / Technical Committee on Signal Processing / Technical Committee on Speech / Special Interest Group on Spoken Language Processing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Poster Presentation] A study of shout detection for clipped speech |
Sub Title (in English) | |
Keyword(1) | shout |
Keyword(2) | deep learning |
Keyword(3) | clipped speech |
Keyword(4) | declipping |
1st Author's Name | Taito Ishida |
1st Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
2nd Author's Name | Kazuhiro Matsuda |
2nd Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
3rd Author's Name | Takahiro Fukumori |
3rd Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
4th Author's Name | Yoichi Yamashita |
4th Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
Date | 2022-03-02 |
Paper # | EA2021-97,SIP2021-124,SP2021-82 |
Volume (vol) | vol.121 |
Number (no) | EA-383,SIP-384,SP-385 |
Page | pp.pp.207-212(EA), pp.207-212(SIP), pp.207-212(SP), |
#Pages | 6 |
Date of Issue | 2022-02-22 (EA, SIP, SP) |