A
András Zolnay
Researcher at RWTH Aachen University
Publications - 9
Citations - 301
András Zolnay is an academic researcher from RWTH Aachen University. The author has contributed to research in topics: Linear discriminant analysis & Word error rate. The author has an hindex of 9, co-authored 9 publications receiving 295 citations.
Papers
More filters
Proceedings ArticleDOI
Acoustic feature combination for robust speech recognition
TL;DR: Experiments performed on the large-vocabulary task VerbMobil II (German conversational speech) show that the accuracy of automatic speech recognition systems can be improved by the combination of different acoustic features.
Proceedings Article
Robust speech recognition using a voiced-unvoiced feature.
TL;DR: A voiced-unvoiced measure was combined with the standard Mel Frequency Cepstral Coefficients using linear discriminant analysis (LDA) to choose the most relevant features for continuous speech recognition.
Proceedings ArticleDOI
Implementing frequency-warping and VTLN through linear transformation of conventional MFCC.
TL;DR: The proposed method exploits the bandlimited interpolation idea (in the frequency-domain) to do the necessary frequency-warping and yields exact results as long as the cepstral coefficients are que-frency limited.
Journal ArticleDOI
Using multiple acoustic feature sets for speech recognition
TL;DR: The results show that the accuracy of automatic speech recognition systems can be significantly improved by the combination of auditory and articulatory motivated features.
Proceedings Article
Feature combination using linear discriminant analysis and its pitfalls.
TL;DR: It is shown that the combination of acoustic features using LDA does not consistently lead to improvements in word error rate, and relative improvements inword error rate of up to 5% were observed for LDA-based combination of multiple acoustic features.