1 code implementation • 13 May 2023 • Kota Dohi, Keisuke Imoto, Noboru Harada, Daisuke Niizumi, Yuma Koizumi, Tomoya Nishida, Harsh Purohit, Ryo Tanabe, Takashi Endo, Yohei Kawaguchi
In 2023 Task 2, we focus on solving the first-shot problem, which is the challenge of training a model on a completely novel machine type.
no code implementations • 5 Apr 2023 • Tomoya Nishida, Takashi Endo, Yohei Kawaguchi
To solve this problem, we propose a domain adaptation method for SSAD where no anomalous data are available for the target domain.
2 code implementations • 13 Jun 2022 • Kota Dohi, Keisuke Imoto, Noboru Harada, Daisuke Niizumi, Yuma Koizumi, Tomoya Nishida, Harsh Purohit, Takashi Endo, Masaaki Yamamoto, Yohei Kawaguchi
We present the task description and discussion on the results of the DCASE 2022 Challenge Task 2: ``Unsupervised anomalous sound detection (ASD) for machine condition monitoring applying domain generalization techniques''.
2 code implementations • 27 May 2022 • Kota Dohi, Tomoya Nishida, Harsh Purohit, Ryo Tanabe, Takashi Endo, Masaaki Yamamoto, Yuki Nikaido, Yohei Kawaguchi
We present a machine sound dataset to benchmark domain generalization techniques for anomalous sound detection (ASD).
no code implementations • 15 Apr 2022 • Tomoya Nishida, Kota Dohi, Takashi Endo, Masaaki Yamamoto, Yohei Kawaguchi
We have developed an unsupervised anomalous sound detection method for machine condition monitoring that utilizes an auxiliary task -- detecting when the target machine is active.
2 code implementations • 21 Jun 2021 • Shoichi Koyama, Tomoya Nishida, Keisuke Kimura, Takumi Abe, Natsuki Ueno, Jesper Brunnström
Two subdatasets are currently available: one consists of IRs in a three-dimensional cuboidal region from a single source, and the other consists of IRs in a two-dimensional square region from an array of 32 sources.
1 code implementation • 19 May 2020 • Kaori Suefusa, Tomoya Nishida, Harsh Purohit, Ryo Tanabe, Takashi Endo, Yohei Kawaguchi
However, when the target machine sound is non-stationary, a reconstruction error tends to be large independent of an anomaly, and its variations increased because of the difficulty of predicting the edge frames.