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.
|Number of pages||4|
|Publication status||Published - 01.04.1994|
|Event||Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing 1994 - Adelaide, Australia|
Duration: 19.04.1994 → 22.04.1994
|Conference||Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing 1994|
|Abbreviated title||ICASSP '94|
|Period||19.04.94 → 22.04.94|