Sampled and discretized of short-time Fourier transform and non-negative matrix factorization: the single-channel source separation case

Jurnal Teknologi dan Sistem Komputer

Yoga Mileniandi¹  Jans Hendry¹  Isnan Nur Rifai¹ 

[1] Department of Electrical Engineering and Informatics, Vocational College, Universitas Gadjah Mada. Yacaranda st., Sekip Unit IV, Yogyakarta, Indonesia 55281, Indonesia;

关键词: dgt;    stft;    nmf;    time-frequency representation;    single-channel source separation;   

DOI  :  10.14710/jtsiskom.2020.13858

来源: DOAJ

【 摘 要 】

The Short-time Fourier transform (STFT) is a popular time-frequency representation in many source separation problems. In this work, the sampled and discretized version of Discrete Gabor Transform (DGT) is proposed to replace STFT within the single-channel source separation problem of the Non-negative Matrix Factorization (NMF) framework. The result shows that NMF-DGT is better than NMF-STFT according to Signal-to-Interference Ratio (SIR), Signal-to-Artifact Ratio (SAR), and Signal-to-Distortion Ratio (SDR). In the supervised scheme, NMF-DGT has a SIR of 18.60 dB compared to 16.24 dB in NMF-STFT, SAR of 13.77 dB to 13.69 dB, and SDR of 12.45 dB to 11.16 dB. In the unsupervised scheme, NMF-DGT has a SIR of 0.40 dB compared to 0.27 dB by NMF-STFT, SAR of -10.21 dB to -10.36 dB, and SDR of -15.01 dB to -15.23 dB.

【 授权许可】

Unknown