Browse > Article
http://dx.doi.org/10.5909/JBE.2014.19.6.819

Online Monaural Ambient Sound Extraction based on Nonnegative Matrix Factorization Method for Audio Contents  

Lee, Seokjin (Department of Electronic Engineering, Kyonggi University)
Publication Information
Journal of Broadcast Engineering / v.19, no.6, 2014 , pp. 819-825 More about this Journal
Abstract
In this paper, monaural ambient component extraction algorithm based on nonnegative matrix factorization (NMF) is described. The ambience component extraction algorithm in this paper is developed for audio upmixing system; Recent researches have shown that they can enhance listener envelopment if the extracted ambient signal is applied into the multichannel audio upmixing system. However, the conventional method stores all of the audio signal and processes all at once, so it cannot be applied to streaming system and digital signal processor (DSP) system. In this paper, the ambient component extraction algorithm based on on-line nonnegative matrix factorization is developed and evaluated to solve the problem. As a result of analysis of the processed signal with spectral flatness measures in the experiment, it was shown that the developed system can extract the ambient signal similarly with the conventional batch process system.
Keywords
Nonnegative Matrix Factorization; Online Nonnegative Matrix Factorization; Multichannel Audio Upmixing; Ambient Signal Extraction;
Citations & Related Records
연도 인용수 순위
  • Reference
1 H. Chung, H. Shim, N. Hahn, and S. B. Chon, "Sound reproduction method by front loudspeaker array for home theater applications," IEEE Transactions on Consumer Electronics, vol. 50, no. 2, pp. 528-534, May 2012.
2 R. Irwan and R. M. Aarts, "Two-to-Five Channel Sound Processing," Journal of Audio Engineering Society, vol. 50, no. 11, pp. 914-926, 2002.
3 C. Avendano and J. M. Jot, "Ambience Extraction and Synthesis from Stereo Signals for Multichannel Audio Up-mix," Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Orlando, USA, 2002.
4 C. Uhle, A. Walther, O. Hellmuth, and J. Herre, "Ambience separation from mono recordings using non-negative matrix factorization," Proc. AES 30th International Conference on Intelligent Audio Environments, Mar. 2007.
5 S. Lee, S. H. Park, K.-M. Sung, "On-line nonnegative matrix factorization method using recursive least squares for acoustic signal processing systems," IEICE Transactions on Fundamentals of Electronics, Communications and Computer Science, vol. E94-A, no. 10, pp. 2022-2026, Oct. 2011.   DOI   ScienceOn
6 D. D. Lee and H. S. Seung, "Learning the Parts of Objects by Non-negative Matrix Factorization," Nature, vol. 401, pp.788-791, Aug. 1999.   DOI   ScienceOn
7 D. D. Lee and H. S. Seung, "Algorithms for non-negative matrix factorization," Proc. Advances in Neural Information Processing 13 (NIPS' 2000), pp. 556-562, 2001.
8 A. Cichocki, R. Zdunek, A. H. Pahn, S. Amari, Nonnegative matrix and tensor factorizations: applications to exploratory multiway daya analysis and blind source separation, John Wiley & Sons, Chichester, 2009.
9 S. Lee, "RLS-based on-line sparse nonnegative matrix factorization method for acoustic signal processing systems," IEICE Transactions on Fundamentals of Electronics, Communications and Computer Science, vol. E96-A, no. 5, pp. 980-985, May 2013.   DOI
10 M. Goto, H. Hashiguchi, T. Nishimura, and R. Oka, "RWC music database: popular, classical, and jazz music database," Proceedings of the 3rd International Conference on Music Information Retrieval (ISMIR 2002), pp. 287-288, Oct. 2002.
11 G. Peeters, "A large set of audio features for sound description (similarity and description) in the CUIDADO project," IRCAM, 2004.