Title :
On the inversion of Mel-frequency cepstral coefficients for speech enhancement applications
Author :
Boucheron, Laura E. ; De Leon, Phillip L.
Author_Institution :
Klipsch Sch. of Electr. & Comput. Eng., New Mexico State Univ., Las Cruces, NM
Abstract :
The use of Mel-frequency cepstral coefficients (MFCCs) is well established in the fields of speech processing, particularly for speaker modeling within a Gaussian mixture model (GMM) speaker recognition system. The use of GMMs for speech enhancement applications has only recently been proposed in the literature; the concept of direct inversion of the MFCCs, however, has not been studied. In this paper we present a means to invert MFCCs for use in speech enhancement applications. Results for cepstral inversion is evaluated on the TIMIT speech corpus using perceptual evaluation of speech quality (PESQ).
Keywords :
Gaussian processes; cepstral analysis; speaker recognition; speech enhancement; GMM; Gaussian mixture model; MFCC inversion; mel-frequency cepstral coefficients; speaker modeling; speaker recognition system; speech enhancement; Acoustic noise; Carbon capture and storage; Cepstral analysis; Speaker recognition; Speech analysis; Speech enhancement; Speech processing; Speech recognition; Speech synthesis; Strontium;
Conference_Titel :
Signals and Electronic Systems, 2008. ICSES '08. International Conference on
Conference_Location :
Krakow
Print_ISBN :
978-83-88309-47-2
Electronic_ISBN :
978-83-88309-52-6
DOI :
10.1109/ICSES.2008.4673475