@article{5cdccd163a4b4c0a8570c434ee84af14,
author = "Szymon Drgas and Tuomas Virtanen and J{\"o}rg L{\"u}cke and Antti Hurmalainen",
abstract = "In this study, we propose an unsupervised method for dictionary learning in audio signals. The new method, called binary nonnegative matrix deconvolution (BNMD), is developed and used to discover patterns from magnitude-scale spectrograms. The BNMD models an audio spectrogram as a sum of delayed patterns having binary gains (activations). Only small subsets of patterns can be active for a given spectrogram excerpt. The proposed method was applied to speaker identification and separation tasks. The experimental results show that dictionaries obtained by the BNMD bring much higher speaker identification accuracies averaged over a range of SNRs from -6 dB to 9 dB (91.3%) than the NMD-based dictionaries (37.8-75.4%). The BNMD also gives a benefit over dictionaries obtained using vector quantization (87.8%). For bigger dictionaries the difference between the BNMD and the vector quantization (VQ) is getting smaller. For the speech separation task the BNMD dictionary gave a slight improvement over the VQ.",
doi = "10.1109/TASLP.2017.2709909",
issn = "2329-9290",
journal = "IEEE-ACM Transactions on Audio Speech and Language Processing",
keywords = "Sparse coding;speaker recognition;speech separation",
month = "8",
number = "8",
pages = "1644--1656",
publisher = "IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC",
title = "{B}inary {N}on-{N}egative {M}atrix {D}econvolution for {A}udio {D}ictionary {L}earning",
volume = "25",
year = "2017",
}