| Paper: | MLSP-P4.6 | ||
| Session: | Audio and Communication Applications | ||
| Time: | Thursday, May 18, 14:00 - 16:00 | ||
| Presentation: | Poster | ||
| Topic: | Machine Learning for Signal Processing: Speech and Audio Processing Applications | ||
| Title: | Room Acoustic Paramter Extraction from Music Signals | ||
| Authors: | Paul Kendrick, Trevor Cox, University of Salford, United Kingdom; Yonggang Zhang, Jonathon Chambers, Cardiff University, United Kingdom; Francis Li, Manchester Metropolitan University, United Kingdom | ||
| Abstract: | A new method employing machine learning techniques and a modified low frequency envelope spectrum estimator, for estimating 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 signal. 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. An artificial neural network is then trained to map envelope spectra onto RT or EDT. Significant improvements in estimation accuracy were found and further investigations show the non-stationarity of music envelopes hinders accurate parameter extraction. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012