Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Single-channel dereverberation using direct MMSE optimization and bidirectional LSTM networks

: Mack, W.; Chakrabarty, S.; Stöter, F.-R.; Braun, S.; Edler, B.; Habets, E.A.P.


Yegnanarayana, B. ; International Speech Communication Association -ISCA-:
Interspeech 2018. Online resource : 2-6 September 2018, Hyderabad
Hyderabad, 2018
DOI: 10.21437/Interspeech.2018
International Speech Communication Association (Interspeech Annual Conference) <2018, Hyderabad>
Fraunhofer IIS ()

Dereverberation is useful in hands-free communication and voice controlled devices for distant speech acquisition. Single-channel dereverberation can be achieved by applying a time-frequency (TF) mask to the short-time Fourier transform (STFT) representation of a reverberant signal. Recent approaches have used deep neural networks (DNNs) to estimate such masks. Previously proposed DNN-based mask estimation methods train a DNN to minimize the mean-squared-error (MSE) between the desired and estimated masks. Recent TF mask estimation methods for signal separation directly minimize instead the MSE between the desired and estimated STFT magnitudes. We apply this direct optimization concept to dereverberation. Moreover, as reverberation exceeds the duration of a single STFT frame, we propose to use a bidirectional long short-term memory (LSTM) network which is able to take the relation between multiple STFT frames into account. We evaluated our method for different reverberation times and source-microphone distances using simulated as well as measured room impulse responses of different rooms. An evaluation of the proposed method and a comparison with a state-of-the-art method demonstrate the superiority of our approach and its robustness to different acoustic conditions.