Sixth European Conference on Speech Communication and Technology
(EUROSPEECH'99)

Budapest, Hungary
September 5-9, 1999

Path-Dependent Kalman Estimation of a Cepstral Bias

Lionel Delphin-Poulat (1), Jérôme Idier (2)

(1) France Télécom CNET/DIH/DIPS, Technopole Anticipa, Lannion, France
(2) Laboratoire des Signaux et Systèmes, Supélec Plateau de Moulon, Gif-sur-Yvette, France

An acoustic mismatch between a given utterance and a model degrades the performance of the speech recognition process. We choose to model speech by Hidden Markov Models (HMMs) in the cepstrum domain and the mis-match by an additive bias. To track the variations of this bias, we explicitly model the way in which the bias can vary by a state equation. We derive a frame-synchronous estimator of this bias based on Kalman recursions. We use this estimator to compensate for the mismatch in the recognition process. Finally, we report recognition experiments carried out over both public switched telephone network (PSTN) and cellular telephone network to show the efficiency of the method in a real context.


Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Delphin-Poulat, Lionel / Idier, Jérôme (1999): "Path-dependent kalman estimation of a cepstral bias", In EUROSPEECH'99, 1303-1306.