Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks

• Published in: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 708 - 712
• Main Authors: Erdogan, Hakan, Hershey, John R., Watanabe, Shinji, Le Roux, Jonathan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.04.2015
• Subjects: ASR; deep networks; Linear programming; LSTM; Noise measurement; Signal to noise ratio; Speech; Speech enhancement; Speech recognition; speech separation; Training

Separation of speech embedded in non-stationary interference is a challenging problem that has recently seen dramatic improvements using deep network-based methods. Previous work has shown that estimating a masking function to be applied to the noisy spectrum is a viable approach that can be improve...