A Post-Filtering Approach Based on Locally Linear Embedding Difference Compensation for Speech Enhancement

Yi-Chiao Wu, Hsin-Te Hwang, Syu-Siang Wang, Chin-Cheng Hsu, Yu Tsao, Hsin-Min Wang


This paper presents a novel difference compensation post-filtering approach based on the locally linear embedding (LLE) algorithm for speech enhancement (SE). The main goal of the proposed post-filtering approach is to further suppress residual noises in SE-processed signals to attain improved speech quality and intelligibility. The proposed system can be divided into offline and online stages. In the offline stage, we prepare paired differences: the estimated difference of SE-processed speech; noisy speech and the ground-truth difference of clean speech; noisy speech. In the online stage, on the basis of estimated difference of a test utterance, we first predict the corresponding ground-truth difference based on the LLE algorithm, and then compensate the noisy speech with the predicted difference. In this study, we integrate a deep denoising autoencoder (DDAE) SE method with the proposed LLE-based difference compensation post-filtering approach. The experiment results reveal that the proposed post-filtering approach obviously enhanced the speech quality and intelligibility of the DDAE-based SE-processed speech in different noise types and signal-to-noise-ratio levels.


 DOI: 10.21437/Interspeech.2017-62

Cite as: Wu, Y., Hwang, H., Wang, S., Hsu, C., Tsao, Y., Wang, H. (2017) A Post-Filtering Approach Based on Locally Linear Embedding Difference Compensation for Speech Enhancement. Proc. Interspeech 2017, 1953-1957, DOI: 10.21437/Interspeech.2017-62.


@inproceedings{Wu2017,
  author={Yi-Chiao Wu and Hsin-Te Hwang and Syu-Siang Wang and Chin-Cheng Hsu and Yu Tsao and Hsin-Min Wang},
  title={A Post-Filtering Approach Based on Locally Linear Embedding Difference Compensation for Speech Enhancement},
  year=2017,
  booktitle={Proc. Interspeech 2017},
  pages={1953--1957},
  doi={10.21437/Interspeech.2017-62},
  url={http://dx.doi.org/10.21437/Interspeech.2017-62}
}