Antonio J. Muñoz-Montoro

Pablo Cabanas-Molero, Antonio J. Munoz-Montoro, Julio Carabias-Orti et al.

This paper presents a novel approach to sound source separation that leverages spatial information obtained during the recording setup. Our method trains a spatial mixing filter using solo passages to capture information about the room impulse response and transducer response at each sensor location. This pre-trained filter is then integrated into a multichannel non-negative matrix factorization (MNMF) scheme to better capture the variances of different sound sources. The recording setup used in our experiments is the typical setup for orchestra recordings, with a main microphone and a close "cardioid" or "supercardioid" microphone for each section of the orchestra. This makes the proposed method applicable to many existing recordings. Experiments on polyphonic ensembles demonstrate the effectiveness of the proposed framework in separating individual sound sources, improving performance compared to conventional MNMF methods.

Antonio J. Muñoz-Montoro, Julio J. Carabias-Orti, Archontis Politis et al.

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.

A. J. Muñoz-Montoro, P. Vera-Candeas, D. Suarez-Dou et al.

In this paper we present a new definition of the distortion matrix for a score following framework based on DTW. The proposal consists of arranging the score information in a sequence of note combinations and learning a spectral pattern for each combination using instrument models. Then, the distortion matrix is computed using these spectral patterns and a novel decomposition of the input signal.