Title :
Modeling the dynamics of speech and noise for speech feature enhancement in ASR
Author :
Windmann, Stefan ; Haeb-Umbach, Reinhold
Author_Institution :
Dept. of Commun. Eng., Paderborn Univ., Paderborn
fDate :
March 31 2008-April 4 2008
Abstract :
In this paper a switching linear dynamical model (SLDM) approach for speech feature enhancement is improved by employing more accurate models for the dynamics of speech and noise. The model of the clean speech feature trajectory is improved by augmenting the state vector to capture information derived from the delta features. Further a hidden noise state variable is introduced to obtain a more elaborated model for the noise dynamics. Approximate Bayesian inference in the SLDM is carried out by a bank of extended Kalman filters, whose outputs are combined according to the a posteriori probability of the individual state models. Experimental results on the AURORA2 database show improved recognition accuracy.
Keywords :
Bayes methods; Kalman filters; channel bank filters; speech enhancement; AURORA2 database; Bayesian inference; a posteriori probability; extended Kalman filter banks; hidden noise state variable; noise dynamics; speech feature enhancement; speech feature trajectory; switching linear dynamical model approach; Automatic speech recognition; Background noise; Cepstral analysis; Communication switching; Jacobian matrices; Speech enhancement; Speech recognition; State estimation; Switches; Vectors; ASR; SLDM; inter-frame correlation; speech feature enhancement; speech recognition;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4244-1483-3
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2008.4518633