TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Binary Non-Negative Matrix Deconvolution for Audio Dictionary Learning

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
Sivut1644-1656
Sivumäärä13
JulkaisuIEEE/ACM Transactions on Audio Speech and Language Processing
Vuosikerta25
Numero8
DOI - pysyväislinkit
TilaJulkaistu - 1 elokuuta 2017
OKM-julkaisutyyppiA1 Alkuperäisartikkeli

Tiivistelmä

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.

Latausten tilastot

Ei tietoja saatavilla