A PERCEPTUALLY ENHANCED BLIND SINGLE-CHANNEL AUDIO SOURCE SEPARATION BY NON-NEGATIVE MATRIX FACTORIZATION


Kirbiz S., Gunsel B.

18th European Signal Processing Conference (EUSIPCO), Aalborg, Danimarka, 23 - 27 Ağustos 2010, ss.731-735 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Basıldığı Şehir: Aalborg
  • Basıldığı Ülke: Danimarka
  • Sayfa Sayıları: ss.731-735
  • İstanbul Teknik Üniversitesi Adresli: Evet

Özet

This paper proposes a 2D Non-negative Matrix Factorization (NMF) based single-channel source separation algorithm that emphasizes perceptually important components of audio. Unlike the existing methods, the proposed scheme performs a psychoacoustic pre-processing on the mixture spectrogram in order to supress audio components that are not critical to human hearing sensation while amplifying the perceptually important ones. This yields the auditory spectrogram referred as sonogram of the observed audio mixture and the individual sources are then extracted by 2D NMF. Test results reported in terms of Signal-to-Distortion-Ratio (SDR), Signal-to-Inference-Ratio (SIR) and Signal-to-Artifact-Ratio (SAR) show that the proposed perceptually enhanced separation improves the quality of decomposed audio sources by 1.5-6.5 dB with a reduced computational complexity.