Sixth European Conference on Speech Communication and Technology
The mel-frequency cepstral coefficients (MFCCs) are frequently used as a speech parameterization in speech recognizers. Practical applications of speech recognition and dialogue systems bring sometimes a requirement to synthesize or reconstruct the speech from the saved or transmitted MFCCs. Presented paper describes an approach to the construction of a MFCC-based speech production system and discusses various possibilities of its excitation.
Full Paper (PDF)
Bibliographic reference. Tychtl, Zbynžk / Psutka, Josef (1999): "Speech production based on the mel-frequency cepstral coefficients", In EUROSPEECH'99, 2335-2338.