Download:
|
by L. Welling, N. Haberl, H. Ney
Proc. EUROSPEECH
http://www.informatik.rwth-aachen.de/I6/PostScript/InterneArbeiten/Welling_FrontEnd_EUROSPEECH97_18Dez98.ps
Add To MetaCart
Abstract:
In this paper we describe experiments with the acoustic front--end of our large vocabulary speech recognition system. In particular, two aspects are studied: 1) linear transforms for feature extraction and 2) the modelling of the emission probabilities. Experiments are reported on a 5000--word task of the ARPA Wall Street Journal database. For the linear transforms our main results are: ffl Filter--bank coefficients yield a word error rate of
Citations
|
3033
|
Pattern Classification and Scene Analysis
– Duda, Hart
- 1973
|
|
929
|
Biing-Hwang Juang, Fundamentals of Speech Recognition
– Rabiner
- 1993
|
|
363
|
Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Sentences
– Davis, Mermelstein
- 1980
|
|
35
|
A Comparison of Several Acoustic Representations for Speech Recognition with Degraded and Undegraded Speech," [58] [59
– Hunt, Lefebvre
- 1989
|
|
30
|
Large vocabulary continuous speech recognition using word graphs
– Aubert, Ney
|
|
17
|
Improvements in connected digit recognition using linear discriminant analysis and mixture densities
– Haeb-Umbach, Geller, et al.
- 1994
|
|
16
|
Acoustic Modeling of Phoneme Units for Continuous Speech Recognition
– Ney
- 1990
|
|
16
|
HTK: Hidden Markov Model Toolkit V1.4
– Young
- 1993
|
|
11
|
Connected Digit Recognition using Statistical Template Matching
– Welling, Ney, et al.
- 1995
|
|
10
|
A Comparative Study of Linear Feature Transformation Techniques for Automatic Speech Recognition
– Eisele, Haeb-Umbach, et al.
- 1996
|
|
8
|
Experiments with linear feature extraction in speech recognition
– Beulen, Welling, et al.
- 1995
|
|
1
|
Ney "State tying for context dependent phoneme models
– Beulen, Branch, et al.
- 1997
|