Implementing frequency-warping and VTLN through linear transformation of conventional MFCC

9th European Conference on Speech Communication and Technology

Volumn , Issue , 2005, Pages 269-272

  Umesh, S ^a   Zolnay, A ^b   Ney, H ^b  

^a INDIAN INSTITUTE OF TECHNOLOGY KANPUR   (India)

^b RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATION THEORY; FREQUENCY DOMAIN ANALYSIS; LINEAR SYSTEMS; MATHEMATICAL TRANSFORMATIONS; SPEECH SYNTHESIS;

CLOSED-FORM SOLUTION; DISCRETE DOMAIN; FREQUENCY-WARPING; RECOMPUTATION;

NATURAL FREQUENCIES;

EID: 33745201218     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. M. Pitz and H. Ney, "Vocal Tract Length Normalization Equals Linear Transformation in Cepstral Space," IEEE Trans. Speech Audio Processing, 2005.
2. S. Molau, M. Pitz, R. Schluter, and H. Ney, "Computing Mel- Frequency Cepstral Coefficients on the Power Spectrum," in Proc. of Int. Conf. on Acoustics, Speech, and Signal Processing, 2001, pp. 73-76.
3. D. Kim, S. Umesh, M. Gales, T. Hain, and P. Woodland, "VTLN in Broadcast News Transcription," in Proc. of Interspeech 2004, 2004.
4. R. Sinha, "Front End Signal Processing For Speaker Normalization," Ph.D. dissertation, Indian Institute of Technology, Kanpur, India, June 2004.
5. S. Umesh, R. Sinha, and S. V. B. Kumar, "An Investigation into Front-End Signal Processing for Speaker Normalization," in Proc. ICASSP, 2004, pp. 345-348.