Title :
Enhanced local feature approach for overlapping sound event recognition
Author :
Dennis, Jonathan ; Huy Dat Tran
Author_Institution :
Inst. for Infocomm Res., A*STAR, Singapore, Singapore
Abstract :
In this paper, we propose a feature-based approach to address the challenging task of recognising overlapping sound events from single channel audio. Our approach is based on our previous work on Local Spectrogram Features (LSFs), where we combined a local spectral representation of the spectrogram with the Generalised Hough Transform (GHT) voting system for recognition. Here we propose to take the output from the GHT and use it as a feature for classification, and demonstrate that such an approach can improve upon the previous knowledge-based scoring system. Experiments are carried out on a challenging set of five overlapping sound events, with the addition of non-stationary background noise and volume change. The results show that the proposed system can achieve a detection rate of 99% and 91% in clean and 0dB noise conditions respectively, which is a strong improvement over our previous work.
Keywords :
Hough transforms; audio signal processing; signal classification; GHT; LSF; enhanced local feature based approach; generalised Hough transform voting system; local spectral representation; local spectrogram features; nonstationary background noise; overlapping sound event recognition; single channel audio; Databases; Feature extraction; Noise; Spectrogram; Speech; Training; Transforms;
Conference_Titel :
Asia-Pacific Signal and Information Processing Association, 2014 Annual Summit and Conference (APSIPA)
Conference_Location :
Siem Reap
DOI :
10.1109/APSIPA.2014.7041646