TUTCRIS - Tampereen teknillinen yliopisto


Multichannel Singing Voice Separation by Deep Neural Network Informed DOA Constrained CNMF



OtsikkoIEEE International Workshop on Multimedia Signal Processing (MMSP)
TilaHyväksytty/In press - 2020
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE International Workshop on Multimedia Signal Processing -
Kesto: 1 tammikuuta 1900 → …


ConferenceIEEE International Workshop on Multimedia Signal Processing
Ajanjakso1/01/00 → …


This work addresses the problem of multichannel source separation combining two powerful approaches, multichannel spectral factorization with recent monophonic deep-learning (DL) based spectrum inference. Individual source spectra at different channels are estimated with a Masker-Denoiser Twin Network (MaD TwinNet), able to model long-term temporal patterns of a musical piece. The monophonic source spectrograms are used within a spatial covariance mixing model based on Complex Non-Negative Matrix Factorization (CNMF) that predicts the spatial characteristics of each source. The proposed framework is evaluated on the task of singing voice separation with a large multichannel dataset. Experimental results show that our joint DL+CNMF method outperforms both the individual monophonic DL-based separation and the multichannel CNMF baseline methods.