| Presentation | 2023-03-01 Anomalous sound detection based on differential features of multi channel acoustic signals considering spatial and temporal variations Shota Nishiyama, Akira Tamamori, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Anomalous sound detection plays an essential role in machine condition management in factory automation. The task of anomalous sound detection is to distinguish between normal and anomalous sounds. Collecting anomalous sounds in advance is difficult because they occur infrequently and are very diverse. Therefore, anomalous sound detection is treated as a problem of only detecting anomalous sounds from normal sounds. Most anomalous sound detection methods target single-channel audio signals. On the other hand, in some factories, multiple microphones can be installed to record multi-channel audio signals. In this study, we propose a feature set that is useful for the anomalous sound detection task, targeting multi-channel audio signals obtained from multiple microphones at different distances from the sound source. In addition to the phase and mel-spectrogram obtained from the complex-spectrogram, their differential features are used as input to the model to account for changes in time and space due to the distance between the microphones and the sound sources. The dataset is a multi-channel audio signal from ToyADMOS. Comparison experiments show that the proposed features significantly improve the AUC, an evaluation index, compared to the accuracy of anomalous sound detection using only the mel-spectrogram as a feature, indicating the usefulness of differential features that take into account temporal and spatial variations. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Anomalous sound detection / multi-channel-signal / differential features |
| Paper # | |
| Date of Issue |
| Conference Information | |
| Committee | SP / IPSJ-SLP / EA / SIP |
|---|---|
| Conference Date | 2023/2/28(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Tomoki Toda(Nagoya Univ.) / Tomoki Toda(Nagoya Univ.) / Kenichi Furuya(Oita Univ.) / Toshihisa Tanaka(Tokyo Univ. Agri.&Tech.) |
| Vice Chair | / / Tatsuya Kako(NTT) / Junki Ono(Tokyo Metropolitan Univ.) / Koichi Ichige(Yokohama National Univ.) / Takayuki Nakachi(Ryukyu Univ.) |
| Secretary | (NTT) / (Univ. of Electro-Comm.) / Tatsuya Kako(NTT) / Junki Ono(Univ. of Electro-Comm.) / Koichi Ichige(NTT) / Takayuki Nakachi(RitsumeikanUniv.) |
| Assistant | Ryo Aihara(Mitsubishi Electric) / Daisuke Saito(Univ. of Tokyo) / Ryo Aihara(Mitsubishi Electric) / Daisuke Saito(Univ. of Tokyo) / Masato Nakayama(Osaka Sangyo Univ.) / Kouhei Yatabe(Tuat) / Taichi Yoshida(UEC) / Shoko Imaizumi(Chiba Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Speech / Special Interest Group on Spoken Language Processing / Technical Committee on Engineering Acoustics / Technical Committee on Signal Processing |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Anomalous sound detection based on differential features of multi channel acoustic signals considering spatial and temporal variations |
| Sub Title (in English) | |
| Keyword(1) | Anomalous sound detection |
| Keyword(2) | multi-channel-signal |
| Keyword(3) | differential features |
| 1st Author's Name | Shota Nishiyama |
| 1st Author's Affiliation | Aichi Institute of Technology(AIT) |
| 2nd Author's Name | Akira Tamamori |
| 2nd Author's Affiliation | Aichi Institute of Technology(AIT) |
| Date | 2023-03-01 |
| Paper # | |
| Volume (vol) | vol.122 |
| Number (no) | EA-387,SIP-388,SP-389 |
| Page | pp.pp.-(), |
| #Pages | |
| Date of Issue | |