Discrete Cepstrum Coefficients as Perceptual Features

Cepstrum coefficients are widely used as features for both speech and music. In this paper, the use of discrete cepstrum coefficients is considered, which are computed from sinusoidal peaks in the short time spectrum. These coefficients are very interesting as features for pattern recognition applications since they allow to represent spectra by points in a multidimensional vector space. A new Mel frequency warping method is proposed that allows to compute the spectral envelope on the Mel scale which, by contrast to current estimation techniques, does not rely on manually set parameters. Furthermore, the robustness and perceptual relevance of the coefficients are studied and improved.

[1]  Jonathan Foote,et al.  Content-based retrieval of music and audio , 1997, Other Conferences.

[2]  J. T. Foote,et al.  "Content-Based Retrieval of Music and Audio," Multimedia Storage and Archiving System II , 1997 .

[3]  E. Moulines,et al.  Spectral envelope estimation using a penalized likelihood criterion , 1997, Proceedings of 1997 Workshop on Applications of Signal Processing to Audio and Acoustics.

[4]  Xavier Rodet,et al.  Automatic Estimation of Control Parameters: An Instance-Based Learning Approach , 2001, ICMC.

[5]  Xavier Rodet,et al.  Spectral Envelope Estimation and Representation for Sound Analysis-Synthesis , 1999, ICMC.

[6]  X. Rodet.  A NEW ESTIMATION TECHNIQUE FOR DETERMINING THE CONTROL PARAMETERS OF A PHYSICAL MODEL OF A TRUMPET Wim D ’ haes , 1992 .

[7]  Stephen McAdams,et al.  Instrument Sound Description in the Context of MPEG-7 , 2000, ICMC.

[8]  Xavier Rodet,et al.  Spectral envelope estimation, representation, and morphing for sound analysis, transformation, and synthesis. , 1999 .

[9]  Eric Moulines,et al.  Estimation of the spectral envelope of voiced sounds using a penalized likelihood approach , 2001, IEEE Trans. Speech Audio Process..

[10]  X. Rodet,et al.  Generalized Discrete Cepstral Analysis for Decorrvolution of Source-Filter System with Discrete Spectra , 1991, Final Program and Paper Summaries 1991 IEEE ASSP Workshop on Applications of Signal Processing to Audio and Acoustics.

[11]  Xavier Rodet,et al.  An Improved Cepstral Method for Deconvolution of Source-Filter Systems with Discrete Spectra: Application to Musical Sound Signals , 1990, ICMC.

[12]  François Pachet,et al.  FINDING SONGS THAT SOUND THE SAME , 2002 .

[13]  Liang Gu,et al.  Perceptual harmonic cepstral coefficients as the front-end for speech recognition , 2000, INTERSPEECH.

[14]  Xavier Rodet.  Musical Sound Signal Analysis/Synthesis: Sinusoidal+Residual and Elementary Waveform Models , 1997 .

[15]  J C Brown.  Computer identification of musical instruments using pattern recognition with cepstral coefficients as features. , 1999, The Journal of the Acoustical Society of America.

[16]  Christian Spevak,et al.  SOUNDSPOTTER – A PROTOTYPE SYSTEM FOR CONTENT-BASED AUDIO RETRIEVAL , 2002 .