FurcaNet: An end-to-end deep gated convolutional, long short-term memory, deep neural networks for single channel speech separation
This work addresses speech separation for applications like hearing aids or voice assistants, but it is incremental as it builds on existing gated convolutional and LSTM methods.
The paper tackles single-channel speech separation by proposing an end-to-end deep learning model combining gated convolutional networks and LSTM, which directly optimizes utterance-level SDR using permutation invariant training, resulting in improved performance on the WSJ0-2mix dataset.
Deep gated convolutional networks have been proved to be very effective in single channel speech separation. However current state-of-the-art framework often considers training the gated convolutional networks in time-frequency (TF) domain. Such an approach will result in limited perceptual score, such as signal-to-distortion ratio (SDR) upper bound of separated utterances and also fail to exploit an end-to-end framework. In this paper we present an integrated simple and effective end-to-end approach to monaural speech separation, which consists of deep gated convolutional neural networks (GCNN) that takes the mixed utterance of two speakers and maps it to two separated utterances, where each utterance contains only one speaker's voice. In addition long short-term memory (LSTM) is employed for long term temporal modeling. For the objective, we propose to train the network by directly optimizing utterance level SDR in a permutation invariant training (PIT) style. Our experiments on the public WSJ0-2mix data corpus demonstrate that this new scheme can produce more discriminative separated utterances and leading to performance improvement on the speaker separation task.