NOVEL COCHLEAR FILTER BASED CEPSTRAL COEFFICIENTS FOR CLASSIFICATION OF UNVOICED FRICATIVES

In this paper, the use of new auditory-based features derived from cochlear filters, have been proposed for classification of unvoiced fricatives. Classification attempts have been made to classify sibilant (i.e., /s/, /sh/) vs. non-sibilants (i.e., /f/, /th/) as well as for fricatives within each sub-category (i.e., intra-sibilants and intra-non-sibilants). Our experimental results indicate that proposed feature set, viz., Cochlear Filterbased Cepstral Coefficients (CFCC) performs better for individual fricative classification (i.e., a jump of 3.41 % in average classification accuracy and a fall of 6.59 % in EER) in clean conditions than the stateof-the-art feature set, viz., Mel Frequency Cepstral Coefficients (MFCC). Furthermore, under signal degradation conditions (i.e., by additive white noise) classification accuracy using proposed feature set drops much slowly (i.e., from 86.73 % in clean conditions to 77.46 % at SNR of 5 dB) than by using MFCC (i.e., from 82.18 % in clean conditions to 46.93 % at SNR of 5 dB).

[1]  B. Moore.  An Introduction to the Psychology of Hearing , 1977 .

[2]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[3]  Craig C. Bader,et al.  Evoked mechanical responses of isolated cochlear outer hair cells. , 1985, Science.

[4]  P. Strevens.  Spectra of Fricative Noise in Human Speech , 1960 .

[5]  Gunnar Fant,et al.  Acoustic Theory Of Speech Production , 1960 .

[6]  Shawn L. Nissen,et al.  An acoustic analysis of voiceless obstruents produced by adults and typically developing children. , 2003 .

[7]  G. W. Hughes,et al.  Spectral Properties of Fricative Consonants , 1956 .

[8]  George P. McCasland.  Noise intensity and spectrum cues of spoken fricatives , 1979 .

[9]  A.P. Benguerel,et al.  Speech analysis , 1981, Proceedings of the IEEE.

[10]  A. Jongman.  Duration of frication noise required for identification of English fricatives. , 1989, The Journal of the Acoustical Society of America.

[11]  W. G. Radley.  Visible Speech , 1948, Nature.

[12]  Stan Davis,et al.  Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Se , 1980 .

[13]  S. Blumstein,et al.  Acoustic characteristics of English voiceless fricatives: a descriptive analysis , 1988 .

[14]  Hermann von Helmholtz,et al.  On the Sensations of Tone , 1954 .

[15]  K. Stevens.  Evidence for the role of acoustic boundaries in the perception of speech sounds , 1981 .

[16]  John E. Markel,et al.  Linear Prediction of Speech , 1976, Communication and Cybernetics.

[17]  H. Gilbert,et al.  Spectral properties of fricative consonants in children. , 1979, The Journal of the Acoustical Society of America.

[18]  A. Jongman,et al.  Acoustic characteristics of English fricatives. , 2000, The Journal of the Acoustical Society of America.

[19]  J. Flanagan.  Speech Analysis, Synthesis and Perception , 1971 .

[20]  S. Jaffard.  Pointwise smoothness, two-microlocalization and wavelet coefficients , 1991 .

[21]  Qi Li,et al.  An Auditory-Based Feature Extraction Algorithm for Robust Speaker Identification Under Mismatched Conditions , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[22]  H. M. Teager,et al.  Evidence for Nonlinear Sound Production Mechanisms in the Vocal Tract , 1990 .

[23]  Sharath Pankanti,et al.  Evaluation techniques for biometrics-based authentication systems (FRR) , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[24]  Qi Li,et al.  An auditory-based transfrom for audio signal processing , 2009, 2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics.

[25]  Yizhar Lavner,et al.  Acoustic-phonetic analysis of fricatives for classification using SVM based algorithm , 2010, 2010 IEEE 26-th Convention of Electrical and Electronics Engineers in Israel.

[26]  Alvin F. Martin,et al.  The DET curve in assessment of detection task performance , 1997, EUROSPEECH.

[27]  S. Blumstein,et al.  On the role of the amplitude of the fricative noise in the perception of place of articulation in voiceless fricative consonants. , 1988, The Journal of the Acoustical Society of America.