High noise robustness has been achieved in speech recognition by using sparse exemplar-based methods with spectrogram windows spanning up to 300 ms. A downside is that a large exe...
Antti Hurmalainen, Jort F. Gemmeke, Tuomas Virtane...
In the past several years, we’ve been studying feature transformation (FT) approaches to robust automatic speech recognition (ASR) which can compensate for possible “distortio...
In previous work we introduced a new missing data imputation method for ASR, dubbed sparse imputation. We showed that the method is capable of maintaining good recognition accurac...
In this paper, we present the Gauss-Newton method as a unified approach to optimizing non-linear noise compensation models, such as vector Taylor series (VTS), data-driven parall...
— Missing feature theory (MFT) has demonstrated great potential for improving the noise robustness in speech recognition. MFT was mostly applied in the log-spectral domain since ...