This talk will address the musical blind source separation problem: given multiple instrument tracks recorded together, how can each be isolated from the others given no additional knowledge about the instrument locations or sounds? There are many advantages to solving the problem: live performances can convey the energy of the performers, and the sound of the room can improve the perceptual quality of the recording, while separating the instrument tracks afterwards allows for more precise equalization and mixing to improve the recording. This thesis proposes a novel approach to the problem using an ambisonic microphone array: the directionality of the microphones in the array provides information about the location of each source and allows for the implementation of a direction of arrival estimator that calculates the position of each source based on the directions that receive the most non-reverberant acoustic energy. Given the directions of arrival, the method performs spatial filtering to virtually steer the microphone array in the desired directions. This approach is compared with a classic non-negative matrix factorization (NMF) approach and a state of the art ambisonic domain filtering approach. The proposed method outperforms NMF in nearly every tested configuration, and outperforms the ambisonic filtering approach in certain high-reverberation cases. Importantly, it is vastly more computationally efficient, working in much less than real time, and introduces less algorithmic noise to the separated tracks.

Melden Sie sich Hier an um die Einladung zu dem Vortrag per E-Mail zu erhalten.
Register here to receive the invitation to this talk via E-Mail.

Zoom ID: 920 8400 8668
Password: 837069