| Presentation | 2022-06-18 Anomalous sound detection using multi-class classifier and reconstructor of its intermediate layer output Keita Matsumoto, Takeshi Yamada, Shoji Makino, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, there has been a growing demand for techniques to detect unknown anomalous sounds by unsupervised learning using only normal sound data. Currently, the most popular method is based on reconstruction of normal sound data. This method uses an autoencoder to reconstruct the input data, and uses the reconstruction error as the anomalous score for anomalous detection. A method combining a binary classifier for normal/anomaly and distance learning in the latent space was recently proposed, assuming that virtual anomalous sound data is prepared at the time of learning. This method learns a binary classifier using normal and virtual anomalous sound data, and incorporates an index based on the center of gravity of the normal and anomalous classes in the latent space into the loss function and anomalous score. In this paper, we integrate these methods to further improve performance. Specifically, we propose a method that combines a multi-class classifier, distance learning on the latent space, and a reconstructor of the intermediate layer output. Experimental results using DCASE2020 Task 2, a task for anomalous sound detection, confirm the effectiveness of the proposed method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | anomalous sound detection / multiclass classifier / reconstructor / metric learning |
| Paper # | SP2022-18 |
| Date of Issue | 2022-06-10 (SP) |
| Conference Information | |
| Committee | SP / IPSJ-MUS / IPSJ-SLP |
|---|---|
| Conference Date | 2022/6/17(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Tomoki Toda(Nagoya Univ.) |
| Vice Chair | |
| Secretary | (NTT) / (Univ. of Electro-Comm.) |
| Assistant | Ryo Aihara(Mitsubishi Electric) / Daisuke Saito(Univ. of Tokyo) |
| Paper Information | |
| Registration To | Technical Committee on Speech / Special Interest Group on Music and Computer / 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) | Anomalous sound detection using multi-class classifier and reconstructor of its intermediate layer output |
| Sub Title (in English) | |
| Keyword(1) | anomalous sound detection |
| Keyword(2) | multiclass classifier |
| Keyword(3) | reconstructor |
| Keyword(4) | metric learning |
| 1st Author's Name | Keita Matsumoto |
| 1st Author's Affiliation | University of Tsukuba(Univ. of Tsukuba) |
| 2nd Author's Name | Takeshi Yamada |
| 2nd Author's Affiliation | University of Tsukuba(Univ. of Tsukuba) |
| 3rd Author's Name | Shoji Makino |
| 3rd Author's Affiliation | Waseda University/University of Tsukuba(Waseda Univ./Univ. of Tsukuba) |
| Date | 2022-06-18 |
| Paper # | SP2022-18 |
| Volume (vol) | vol.122 |
| Number (no) | SP-81 |
| Page | pp.pp.77-81(SP), |
| #Pages | 5 |
| Date of Issue | 2022-06-10 (SP) |