Multi-modal Blind Source Separation with Microphones and Blinkies
This work addresses source separation for audio processing applications, offering an incremental improvement by integrating blinkies to mitigate microphone array limitations.
The paper tackles blind source separation by combining microphone arrays with low-rate sound power sensors called blinkies, achieving up to 8 dB better median separation performance than independent vector analysis with reduced variability.
We propose a blind source separation algorithm that jointly exploits measurements by a conventional microphone array and an ad hoc array of low-rate sound power sensors called blinkies. While providing less information than microphones, blinkies circumvent some difficulties of microphone arrays in terms of manufacturing, synchronization, and deployment. The algorithm is derived from a joint probabilistic model of the microphone and sound power measurements. We assume the separated sources to follow a time-varying spherical Gaussian distribution, and the non-negative power measurement space-time matrix to have a low-rank structure. We show that alternating updates similar to those of independent vector analysis and Itakura-Saito non-negative matrix factorization decrease the negative log-likelihood of the joint distribution. The proposed algorithm is validated via numerical experiments. Its median separation performance is found to be up to 8 dB more than that of independent vector analysis, with significantly reduced variability.