@ARTICLE{Liu_Houguang_Speech_2020,
 author={Liu, Houguang and Wang, Wenbo and Xue, Lin and Yang, Jianhua and Wang, Zhihua and Hua, Chunli},
 volume={vol. 45},
 number={No 4},
 journal={Archives of Acoustics},
 pages={565–572},
 howpublished={online},
 year={2020},
 publisher={Polish Academy of Sciences, Institute of Fundamental Technological Research, Committee on Acoustics},
 abstract={Nonnegative matrix factorization (NMF) is one of the most popular machine learning tools for speech enhancement (SE). However, there are two problems reducing the performance of the traditional NMFbased SE algorithms. One is related to the overlap-and-add operation used in the short time Fourier transform (STFT) based signal reconstruction, and the other is the Euclidean distance used commonly as an objective function; these methods can cause distortion in the SE process. In order to get over these shortcomings, we propose a novel SE joint framework which combines the discrete wavelet packet transform (DWPT) and the Itakura-Saito nonnegative matrix factorisation (ISNMF). In this approach, the speech signal was first split into a series of subband signals using the DWPT. Then, the ISNMF was used to enhance the speech for each subband signal. Finally, the inverse DWPT (IDWT) was utilised to reconstruct these enhanced speech subband signals. The experimental results show that the proposed joint framework effectively enhances the performance of speech enhancement and performs better in the unseen noise case compared to the traditional NMF methods.},
 type={Article},
 title={Speech Enhancement Based on Discrete Wavelet Packet Transform and Itakura-Saito Nonnegative Matrix Factorisation},
 URL={http://czasopisma.pan.pl/Content/117166/PDF/aoa.2020.134072.pdf},
 doi={10.24425/aoa.2020.134072},
 keywords={speech enhancement, discrete wavelet packet transform, nonnegative matrix factorisation, Itakura-Saito divergence},
}