Thumbnail
Access Restriction
Open

Author Wölfel, Matthias ♦ Mcdonough, John ♦ Waibel, Alex
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Time-domain Technique ♦ Mvdr Spectral Estimate ♦ Robust Feature ♦ All-pole Model ♦ Common Mvdr ♦ Switchboard Corpus ♦ Good Effect ♦ Spectral Envelope ♦ Word Error Rate ♦ Spectral Estimation ♦ Warped Short Time Frequency ♦ Minimum Variance Distortionless Response ♦ Robust Speech Recognition ♦ Noisy Condition ♦ Fourier Transform ♦ Signal Processing Literature ♦ Speech Recognition Experiment
Description In Proc. IEEE Automatic Speech Recognition and Understanding Workshop
Spectral estimation based on the minimum variance distortionless response (MVDR) is well-known in the signal processing literature and has been shown to be superior to linear prediction for robust speech recognition. In this work we propose two techniques to improve the resolution and the robustness of the MVDR spectral estimate: The first is a time-domain technique to estimate an all-pole model based on the warped short time frequency axis such as the Melfrequency. The second is a method for scaling the height of the spectral envelope in order to extract robust features for large vocabulary continuous speech recognition systems which must operate in noisy conditions. Moreover, we show that these two techniques can be combined to good effect. In a series of speech recognition experiments on the Switchboard Corpus, the combination of our proposed approaches achieved a word error rate (WER) of 35.9%, which is clearly superior to the 37.0 % WER obtained by the common MVDR and the 37.2 % WER obtained by the widely used Fourier transform. 1.
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 2003-01-01
Publisher Institution Universität Karlsruhe (th