论文信息 - Cepstral mean and variance normalization in the model domain

Cepstral mean and variance normalization in the model domain

In prior work we have demonstrated the noise robustness of a novel microphone solution, the PARAT earplug communication terminal. Here we extend that work with results for the ETSI Advanced Front-End and segmental cepstral mean and variance normalization (CMVN). We also propose a method for doing CMVN in the model domain. This removes the need to train models on normalized features, which may significantly extend the applicability of CMVN. The recognition results are comparable to those of the traditional approach.

Ole Morten Strand | O. M. Strand | A. Egeberg | Andreas Egeberg

[1] O. M. Strand,et al. AUTOMATIC RECOGNITION OF SPOKEN DIGIT STRINGS IN NOISY ENVIRONMENTS WITH THE PARAT MICROPHONE , 2003 .

[2] Hynek Hermansky,et al. Multi-band and adaptation approaches to robust speech recognition , 1997, EUROSPEECH.

[3] Trym Holter,et al. On the feasibility of ASR in extreme noise using the PARAT earplug communication terminal , 2003, 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721).

[4] John S. D. Mason,et al. On the limitations of cepstral features in noise , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[5] Jean-Claude Junqua,et al. Robustness in Automatic Speech Recognition: Fundamentals and Applications , 1995 .

[6] Olli Viikki,et al. Cepstral domain segmental feature vector normalization for noise robust speech recognition , 1998, Speech Commun..