TR2026-162

When Speech is Noise: Speech Removal for Machine Anomaly Detection

    •  Edo, T., Wichern, G., Fujimura, T., Boeddeker, C., Masuyama, Y., Richter, J., Saijo, K., Le Roux, J., "When Speech is Noise: Speech Removal for Machine Anomaly Detection", Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE), October 2026.
      BibTeX TR2026-162 PDF
      • @inproceedings{Edo2026oct,
      • author = {Edo, Takahiro and Wichern, Gordon and Fujimura, Takuya and Boeddeker, Christoph and Masuyama, Yoshiki and Richter, Julius and Saijo, Kohei and {Le Roux}, Jonathan},
      • title = {{When Speech is Noise: Speech Removal for Machine Anomaly Detection}},
      • booktitle = {Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)},
      • year = 2026,
      • month = oct,
      • url = {https://www.merl.com/publications/TR2026-162}
      • }
  • MERL Contacts:
  • Research Areas:

    Artificial Intelligence, Machine Learning, Speech & Audio

Abstract:

Machine anomaly detection is widely used for predictive maintenance. When anomalous sound detection (ASD) systems are deployed in environments such as factories, we have noticed that a large number of false alarms are caused by human speech and nonverbal sounds such as laughing. In this paper, we investigate using a controlled evaluation framework where we contaminate existing ASD datasets with human vocalizations under various signal-to-noise ratios and durations. Experiments on different ASD systems show that human vocalizations significantly degrade anomaly detection performance. We further demonstrate that training with vocalization-contaminated data and applying source separation as a front-end both mitigate this degradation and partially restore anomaly-score distributions towards uncontaminated machine behavior.