CHALLENGES IN DEPLOYING A MICROPHONE ARRAY TO LOCALIZE AND SEPARATE SOUND SOURCES IN REAL AUDITORY SCENES

Analyzing the auditory scene of real environments is challeng-ing partly because an unknown number and type of sound sources are observed at the same time and partly because these sounds are observed on a significantly different sound pressure level at the mi-crophone. These are difficult problems even with state-of-the-art sound source localization and separation methods. In this paper, we exploit two such methods using a microphone array: (1) Bayesian nonparametric microphone array processing (BNP-MAP), which is capable of separating and localizing sound sources when the num-ber of sound sources is unspecified, and (2) robot audition soft-ware “HARK ” is capable of separating and localizing in real time. Through experimentation, we found that BNP-MAP is more robust against differences in the sound pressure levels of the source signals and in the spatial closeness of source positions. Experiments analyz-ing real scenes of human conversations recorded in a big exhibition hall and bird calling recorded at a natural park demonstrate the effi-cacy and applicability of BNP-MAP. Index Terms — Auditory scene analysis, Bayesian nonparamet-rics, simultaneous sound source localization and separation, sounds of different volume, unknown time-varying number of sources 1