MMSE estimation of log-filter bank energies for robust speech recognition
In this paper, we derive a minimum mean square error log-filterbank energy estimator for environment-robust automatic speech recognition. While several such estimators exist within the literature, most involve trade-offs between simplifications of the log-filterbank noise distortion model and analytical tractability. To avoid this limitation, we extend a well known spectral domain noise distortion model for use in the log-filterbank energy domain. To do this, several mathematical transformations are developed to transform spectral domain models into filterbank and log-filterbank energy models. As a result, a new estimator is developed that allows for robust estimation of both log-filterbank energies and subsequent Mel-frequency cepstral coefficients. The proposed estimator is evaluated over the Aurora2, and RM speech recognition tasks, with results showing a significant reduction in word recognition error over both baseline results and several competing estimators.
Artificial Intelligence and Image Processing not elsewhere classified