Room acoustic parameter extraction from music signals

Kendrick, P; Cox, TJ; Zhang, Y; Chambers, JA; Li, FF

Abstract

A new method, employing machine learning techniques and a modified low frequency envelope spectrum estimator, for estimating important room acoustic parameters including reverberation time (RT) and early decay time (EDT) from received music signals has been developed. It overcomes drawbacks found in applying music signals directly to the envelope spectrum detector developed for the estimation of RT from speech signals. The octave band music signal is first separated into sub bands corresponding to notes on the equal temperament scale and the level of each note normalised before applying an envelope spectrum detector. A typical artificial neural network is then trained to map these envelope spectra onto RT or EDT. Significant improvements in estimation accuracy were found and further investigations confirmed that the non-stationary nature of music envelopes is a major technical challenge hindering accurate parameter extraction from music and the proposed method to some extent circumvents the difficulty.

Citation

Kendrick, P., Cox, T., Zhang, Y., Chambers, J., & Li, F. (2006). Room acoustic parameter extraction from music signals. Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing, 5, V-801. https://doi.org/10.1109/ICASSP.2006.1661397

• Journal Article Type: Article
• Conference Name: 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings
• Publication Date: Jan 1, 2006
• Deposit Date: May 11, 2016
• Journal: Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on (Volume:2 )
• Print ISSN: 1520-6149
• Publisher: Institute of Electrical and Electronics Engineers
• Volume: 5
• Pages: V-801
• Book Title: 2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings
• DOI: https://doi.org/10.1109/ICASSP.2006.1661397
• Publisher URL: http://dx.doi.org/10.1109/ICASSP.2006.1661397
• Related Public URLs: http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=11024
• Additional Information: Event Type : Conference