LAUSR

The goal of this research is to automatically analyze a spatial auditory scene using a 16-channel spherical microphone array and produce an automatic transcript of events that occurred in different directions. The system can be used to establish an automatic protocol for collaborative business meetings or to monitor natural environments. This paper focuses on the automatic data collection of environmental and animal sounds in conjunction with the RPI/IBM Jefferson Project to sensor Lake George, NY. The amount of audio data required for bioacoustics monitoring and other applications is often too large to manually sort the data. Consequently, automatic environmental sound recognition techniques have to be applied to automatically (1) identify and extract relevant acoustic stimuli and (2) classify these stimuli after a training period. Using spatial audio data collected over days in forested areas in Upstate New York, information is automatically extracted and analyzed to find the most relevant parts of thes...