Subband conversion for feature extraction from compressed audio

作者: Tobias Friedrich , Matthias Gruhne , Gerald Schuller

DOI: 10.1109/ICASSP.2008.4517585

关键词:

摘要: We describe an efficient conversion method, which directly converts a desired spectral representation from compressed audio material. The method provides feature extraction algorithm with suitable complex frequency of signal. presented allows us to trade off computational complexity accuracy. then test several operating points MPEG system. That leads, in general, reduction the O (N log N) O(N), compared conventional first decoding and applying DFT resulting time domain

参考文章(9)
Eric Allamanche, Content-based Identification of Audio Material Using MPEG-7 Low Level Description. international symposium/conference on music information retrieval. ,(2001)
R.K. Sande, B. Anantharaman, An efficient VLSI/FPGA architecture for combining an analysis filterbank following a synthesis filterbank international symposium on circuits and systems. ,vol. 3, pp. 517- 520 ,(2004) , 10.1109/ISCAS.2004.1328797
A.B. Touimi, A. Mouhssine, Efficient conversion method between subband domain representations international conference on multimedia and expo. pp. 406- 409 ,(2005) , 10.1109/ICME.2005.1521446
Jae-Beom Lee, A. Eleftheriadis, 2-D transform-domain resolution translation IEEE Transactions on Circuits and Systems for Video Technology. ,vol. 10, pp. 704- 714 ,(2000) , 10.1109/76.856448
G.D.T. Schuller, T. Karp, Modulated filter banks with arbitrary system delay: efficient implementations and the time-varying case IEEE Transactions on Signal Processing. ,vol. 48, pp. 737- 748 ,(2000) , 10.1109/78.824669
A.N. Skodras, Direct transform to transform computation IEEE Signal Processing Letters. ,vol. 6, pp. 202- 204 ,(1999) , 10.1109/97.774865
J.B. Lee, B.G. Lee, Transform domain filtering based on pipelining structure IEEE Transactions on Signal Processing. ,vol. 40, pp. 2061- 2064 ,(1992) , 10.1109/78.150006