Detection of Abnormal Sound Using Multi-stage GMM for Surveillance Microphone
Autor: | Masashi Ito, Shozo Makino, Akihito Aiba, Akinori Ito |
---|---|
Rok vydání: | 2009 |
Předmět: |
geography
Percentile geography.geographical_feature_category Audio signal Computer science business.industry Microphone Speech recognition Pattern recognition Mixture model symbols.namesake Feature (computer vision) otorhinolaryngologic diseases symbols Artificial intelligence business Gaussian process Sound (geography) Event (probability theory) |
Zdroj: | IAS |
Popis: | We developed a system that detects abnormal sound from sound signal observed by a surveillance microphone. Our system learns the “normal sound” from observation of the microphone, and then detects sounds never observed before as “abnormal sounds.” To this end, we developed a technique that uses multiple GMMs for modeling different levels of sound events efficiently. We also consider how to determine thresholds of GMM switching and event detection.As a result, we obtained almost same detection performance using the percentile method to the manually optimized GMMs. Besides, we exploited the segment-based feature, which gave the best result among all methods. |
Databáze: | OpenAIRE |
Externí odkaz: |