On the optimality of ideal binary time-frequency masks
Speech Communication
Model-based expectation-maximization source separation and localization
IEEE Transactions on Audio, Speech, and Language Processing
IEEE Transactions on Audio, Speech, and Language Processing - Special issue on processing reverberant speech: methodologies and applications
Sparse imputation for large vocabulary noise robust ASR
Computer Speech and Language
Proceedings of the Second Symposium on Information and Communication Technology
Computer Speech and Language
A coherence-based noise reduction algorithm for binaural hearing aids
Speech Communication
Hi-index | 0.00 |
This paper describes a perceptually motivated computational auditory scene analysis (CASA) system that combines sound separation according to spatial location with the "missing data" approach for robust speech recognition in noise. Missing data time-frequency masks are created using probability distributions based on estimates of interaural time and level differences (ITD and ILD) for mixed utterances in reverberated conditions; these masks indicate which regions of the spectrum constitute reliable evidence of the target speech signal. A number of experiments compare the relative efficacy of the binaural cues when used individually and in combination. We also investigate the ability of the system to generalize to acoustic conditions not encountered during training. Performance on a continuous digit recognition task using this method is found to be good, even in a particularly challenging environment with three concurrent male talkers.