Random forest classification based acoustic event detection utilizing contextual-information and bottleneck features

PATTERN RECOGNITION

卷:81

Article

Xia, Xianjun¹  Togneri, Roberto¹  Sohel, Ferdous²  Huang, David¹ 

[1] Univ Western Australia, Sch Elect Elect & Comp Engn, 35 Stirling Highway, Perth, WA 6009, Australia

[2] Murdoch Univ, Sch Engn & Informat Technol, 90 South St, Murdoch, WA 6150, Australia

关键词: Acoustic event detection;    Contextual information;    Global bottleneck features;    Category-specific bottleneck features;   

DOI  :  10.1016/j.patcog.2018.03.025

来源: Elsevier

【 摘 要 】

The variety of event categories and event boundary information have resulted in limited success for acoustic event detection systems. To deal with this, we propose to utilize the long contextual information, low-dimensional discriminant global bottleneck features and category-specific bottleneck features. By concatenating several adjacent frames together, the use of contextual information makes it easier to cope with acoustic signals with long duration. Global and category-specific bottleneck features can extract the prior knowledge of the event category and boundary, which is ideally matched by the task of an event detection system. Evaluations on the UPC-TALP and ITC-IRST databases of highly variable acoustic events demonstrate the effectiveness of the proposed approaches by achieving a 5.30% and 4.44% absolute error rate improvement respectively compared to the state of art technique. (C) 2018 Elsevier Ltd. All rights reserved.

【 授权许可】

Free