Non-linear regression based feature extraction for connected-word recognition in noise

F. Seide, A. Mertins

Abstract

This paper shows the application of non-linear regression to robust feature extraction for noisy speech recognition. In this approach, a non-linear estimator is used to compute noise invariant features from non-linear combinations of noise contaminated observations. The observations may be short-term subband-energies obtained from a filter bank analysis, cepstral coefficients of linear prediction coefficients. Instead of training the hidden Markov models (HMMs) under various noise conditions, they can be trained with clean data. The results show that this method leads to error rates comparable to those achieved by training in the presence of noise.
Original languageEnglish
Pages85-88
Number of pages4
DOIs
Publication statusPublished - 01.04.1994
EventProceedings of IEEE International Conference on Acoustics, Speech and Signal Processing 1994 - Adelaide, Australia
Duration: 19.04.199422.04.1994

Conference

ConferenceProceedings of IEEE International Conference on Acoustics, Speech and Signal Processing 1994
Abbreviated titleICASSP '94
Country/TerritoryAustralia
CityAdelaide
Period19.04.9422.04.94

Fingerprint

Dive into the research topics of 'Non-linear regression based feature extraction for connected-word recognition in noise'. Together they form a unique fingerprint.

Cite this