This paper presents a two stages artificial bandwidth extension (ABE) framework which combine deep bidirectional Long Short Term Memory (BLSTM) recurrent neural network with exemplar-based sparse representation to estimate missing frequency band. It demonstrates the suitability of proposed method for modeling log power spectra of speech signals in ABE. The BLSTM-RNN which can capture information from anywhere in the feature sequence is used to estimate the log power spectra in the high-band firstly and the exemplar-based sparse representation which could alleviate the over-smoothing problem is applied to generated log power spectra in the second stage. In addition, rich acoustic features in the low-band are considered to reduce the reconstruction error. Experimental results demonstrate that the proposed framework can achieve significant improvements in both objective and subjective measures over the different baseline methods.
Cite as: Liu, B., Tao, J. (2016) A Novel Research to Artificial Bandwidth Extension Based on Deep BLSTM Recurrent Neural Networks and Exemplar-Based Sparse Representation. Proc. Interspeech 2016, 3778-3782, doi: 10.21437/Interspeech.2016-772
@inproceedings{liu16k_interspeech,
author={Bin Liu and Jianhua Tao},
title={{A Novel Research to Artificial Bandwidth Extension Based on Deep BLSTM Recurrent Neural Networks and Exemplar-Based Sparse Representation}},
year=2016,
booktitle={Proc. Interspeech 2016},
pages={3778--3782},
doi={10.21437/Interspeech.2016-772}
}