AES E-Library

L. Cheng, C. Zheng, R. Peng, and X. Li, "Improvement of DNN-Based Speech Enhancement with Non-Normalized Features by Using an Automatic Gain Control," Paper 10256, (2019 October.). doi: L. Cheng, C. Zheng, R. Peng, and X. Li, "Improvement of DNN-Based Speech Enhancement with Non-Normalized Features by Using an Automatic Gain Control," Paper 10256, (2019 October.). doi:
Abstract: Speech enhancement performance may degrade when the peak level of the noisy speech is significantly different from the training datasets in Deep Neural Networks (DNN)-based speech enhancement algorithms, especially when the non-normalized features are used in practical applications, such as log-power spectra. To overcome this shortcoming, we introduce an automatic gain control (AGC) method as a preprocessing technique. By doing so, we can train the model with the same peak level of all the speech utterances. To further improve the proposed DNN-based algorithm, the feature compensation method is combined with the AGC method. Experimental results indicate that the proposed algorithm can maintain consistent performance when the peak of the noisy speech changes in a large range.

@article{cheng2019improvement,
author={cheng, linjuan and zheng, chengshi and peng, renhua and li, xiaodong},
journal={journal of the audio engineering society},
title={improvement of dnn-based speech enhancement with non-normalized features by using an automatic gain control},
year={2019},
volume={},
number={},
pages={},
doi={},
month={october},} @article{cheng2019improvement,
author={cheng, linjuan and zheng, chengshi and peng, renhua and li, xiaodong},
journal={journal of the audio engineering society},
title={improvement of dnn-based speech enhancement with non-normalized features by using an automatic gain control},
year={2019},
volume={},
number={},
pages={},
doi={},
month={october},
abstract={speech enhancement performance may degrade when the peak level of the noisy speech is significantly different from the training datasets in deep neural networks (dnn)-based speech enhancement algorithms, especially when the non-normalized features are used in practical applications, such as log-power spectra. to overcome this shortcoming, we introduce an automatic gain control (agc) method as a preprocessing technique. by doing so, we can train the model with the same peak level of all the speech utterances. to further improve the proposed dnn-based algorithm, the feature compensation method is combined with the agc method. experimental results indicate that the proposed algorithm can maintain consistent performance when the peak of the noisy speech changes in a large range.},}

TY - paper
TI - Improvement of DNN-Based Speech Enhancement with Non-Normalized Features by Using an Automatic Gain Control
SP - EP -
AU - Cheng, Linjuan
AU - Zheng, Chengshi
AU - Peng, Renhua
AU - Li, Xiaodong
PY - 2019
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2019 TY - paper
TI - Improvement of DNN-Based Speech Enhancement with Non-Normalized Features by Using an Automatic Gain Control
SP - EP -
AU - Cheng, Linjuan
AU - Zheng, Chengshi
AU - Peng, Renhua
AU - Li, Xiaodong
PY - 2019
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2019
AB - Speech enhancement performance may degrade when the peak level of the noisy speech is significantly different from the training datasets in Deep Neural Networks (DNN)-based speech enhancement algorithms, especially when the non-normalized features are used in practical applications, such as log-power spectra. To overcome this shortcoming, we introduce an automatic gain control (AGC) method as a preprocessing technique. By doing so, we can train the model with the same peak level of all the speech utterances. To further improve the proposed DNN-based algorithm, the feature compensation method is combined with the AGC method. Experimental results indicate that the proposed algorithm can maintain consistent performance when the peak of the noisy speech changes in a large range.