Speech Dereverberation with Context-aware Recurrent Neural Networks
This work addresses speech quality enhancement for audio processing applications, representing an incremental advance with specific performance gains.
The paper tackles speech dereverberation by estimating spectral magnitude from reverberant speech using a model with convolutional and recurrent neural networks, achieving improvements of up to 0.4 on PESQ, 0.3 on STOI, and 1.0 on POLQA compared to reverberant speech.
In this paper, we propose a model to perform speech dereverberation by estimating its spectral magnitude from the reverberant counterpart. Our models are capable of extracting features that take into account both short and long-term dependencies in the signal through a convolutional encoder (which extracts features from a short, bounded context of frames) and a recurrent neural network for extracting long-term information. Our model outperforms a recently proposed model that uses different context information depending on the reverberation time, without requiring any sort of additional input, yielding improvements of up to 0.4 on PESQ, 0.3 on STOI, and 1.0 on POLQA relative to reverberant speech. We also show our model is able to generalize to real room impulse responses even when only trained with simulated room impulse responses, different speakers, and high reverberation times. Lastly, listening tests show the proposed method outperforming benchmark models in reduction of perceived reverberation.