DNN Training Based on Classic Gain Function for Single-channel Speech Enhancement and Recognition
Authors:
- 1 May 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 910-914
Abstract
For conventional single-channel speech enhancement based on noise power spectrum, the speech gain function, which suppresses background noise at each time-frequency bin, is calculated by prior signal-to-noise-ratio (SNR). Hence, accurate prior SNR estimation is paramount for successful noise suppression. Accordingly, we have proposed a single-channel approach to combine conventional and deep learning techniques for speech enhancement and automatic speech recognition (ASR) recently. However, the combination process is at the testing stage, which is time-consuming with a complicated procedure. In this study, the gain function of classic speech enhancement will be utilized to optimize the ideal ratio mask based deep neural network (DNN-IRM) at the training stage, denoted as GF-DNN-IRM. And at the testing stage, the estimated IRM by GF-DNN-IRM model is directly used to generate enhanced speech without involving the conventional speech enhancement process. In addition, DNNs with less parameters in the causal processing mode are also discussed. Experiments of the CHiME-4 challenge task show that our proposed algorithm can achieve a relative word error rate reduction of 6.57% on RealData test set comparing to unprocessed speech without acoustic model retraining in causal mode, while the traditional DNN-IRM method fails to improve ASR performance in this case.Keywords
This publication has 21 references indexed in Scilit:
- The third ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselines2015
- Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR2015
- A Regression Approach to Speech Enhancement Based on Deep Neural NetworksIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- On Training Targets for Supervised Speech SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- Oracle estimators for the benchmarking of source separation algorithmsSignal Processing, 2007
- Noise spectrum estimation in adverse environments: improved minima controlled recursive averagingIEEE Transactions on Speech and Audio Processing, 2003
- Speech enhancement for non-stationary noise environmentsSignal Processing, 2001
- Elimination of the musical noise phenomenon with the Ephraim and Malah noise suppressorIEEE Transactions on Speech and Audio Processing, 1994
- Speech enhancement using a minimum-mean square error short-time spectral amplitude estimatorIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984
- Suppression of acoustic noise in speech using spectral subtractionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979