M
Michael Pitz
Researcher at RWTH Aachen University
Publications - 20
Citations - 823
Michael Pitz is an academic researcher from RWTH Aachen University. The author has contributed to research in topics: Word error rate & Normalization (statistics). The author has an hindex of 11, co-authored 20 publications receiving 789 citations. Previous affiliations of Michael Pitz include BMW.
Papers
More filters
Proceedings ArticleDOI
Computing Mel-frequency cepstral coefficients on the power spectrum
TL;DR: The presented approach simplifies the speech recognizers front end by merging subsequent signal analysis steps into a single one, which avoids possible interpolation and discretization problems and results in a compact implementation.
Journal ArticleDOI
Vocal tract normalization equals linear transformation in cepstral space
Michael Pitz,Hermann Ney +1 more
TL;DR: In this paper, the Jacobian determinant of the transformation matrix is computed analytically for three typical warping functions and it is shown that the matrices are diagonal dominant and thus can be approximated by quindiagonal matrices.
Proceedings ArticleDOI
Histogram based normalization in the acoustic feature space
TL;DR: It is shown that histogram normalization performs best if applied both in training and recognition, and that smoothing the target histogram obtained on the training data is also helpful.
Proceedings Article
Vocal tract normalization equals linear transformation in cepstral space.
TL;DR: It is shown that VTN can be viewed as a special case of Maximum Likelihood Linear Regression (MLLR), which can explain previous experimental results that improvements obtained by VTN and subsequent MLLR are not additive in some cases.
Proceedings Article
Vocal tract normalization as linear transformation of MFCC
Michael Pitz,Hermann Ney +1 more
TL;DR: This paper shows that Mel-frequency warping can equally well be integrated into the framework of VTN as linear transformation on the cepstrum and there is a strong interdependence ofVTN and Maximum Likelihood Linear Regression for the case of Gaussian emission probabilities.