Paper Abstract and Keywords |
Presentation |
2023-03-01 14:40
Anomalous sound detection based on differential features of multi channel acoustic signals considering spatial and temporal variations Shota Nishiyama, Akira Tamamori (AIT) |
Abstract |
(in Japanese) |
(See Japanese page) |
(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) |
(in English) |
Anomalous sound detection / multi-channel-signal / differential features / / / / / |
Reference Info. |
IEICE Tech. Rep. |
Paper # |
|
Date of Issue |
|
ISSN |
Online edition: ISSN 2432-6380 |
Download PDF |
|
Conference Information |
Committee |
SP IPSJ-SLP EA SIP |
Conference Date |
2023-02-28 - 2023-03-01 |
Place (in Japanese) |
(See Japanese page) |
Place (in English) |
|
Topics (in Japanese) |
(See Japanese page) |
Topics (in English) |
|
Paper Information |
Registration To |
SP |
Conference Code |
2023-02-SP-SLP-EA-SIP |
Language |
Japanese |
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 |
Keyword(4) |
|
Keyword(5) |
|
Keyword(6) |
|
Keyword(7) |
|
Keyword(8) |
|
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) |
3rd Author's Name |
|
3rd Author's Affiliation |
() |
4th Author's Name |
|
4th Author's Affiliation |
() |
5th Author's Name |
|
5th Author's Affiliation |
() |
6th Author's Name |
|
6th Author's Affiliation |
() |
7th Author's Name |
|
7th Author's Affiliation |
() |
8th Author's Name |
|
8th Author's Affiliation |
() |
9th Author's Name |
|
9th Author's Affiliation |
() |
10th Author's Name |
|
10th Author's Affiliation |
() |
11th Author's Name |
|
11th Author's Affiliation |
() |
12th Author's Name |
|
12th Author's Affiliation |
() |
13th Author's Name |
|
13th Author's Affiliation |
() |
14th Author's Name |
|
14th Author's Affiliation |
() |
15th Author's Name |
|
15th Author's Affiliation |
() |
16th Author's Name |
|
16th Author's Affiliation |
() |
17th Author's Name |
|
17th Author's Affiliation |
() |
18th Author's Name |
|
18th Author's Affiliation |
() |
19th Author's Name |
|
19th Author's Affiliation |
() |
20th Author's Name |
|
20th Author's Affiliation |
() |
Speaker |
Author-1 |
Date Time |
2023-03-01 14:40:00 |
Presentation Time |
5 minutes |
Registration for |
SP |
Paper # |
|
Volume (vol) |
vol.122 |
Number (no) |
no.387(EA), no.388(SIP), no.389(SP) |
Page |
|
#Pages |
|
Date of Issue |
|