Abstract: This disclosure sets forth a system for detecting and determining the onset times of one or more impulsive acoustic events across multiple channels of audio. Audio is segmented into chunks of predefined length and then processed for detecting acoustic onsets, including cross-validating and refining the estimated acoustic onsets to the level of an audio sample. The output of the system is a list of channel-specific timestamped indices corresponding to the audio samples of the onsets of each impulsive acoustic event in the current segment of audio.

Abstract: This disclosure sets forth a system for achieving robust acoustic event detection and source localization using a geographically distributed array of sensor nodes and a set of methods for coordinated dissemination, retrieval, and fusion of acoustic sensor data. A centralized server is programmed to passively receive succinct acoustic alerts, package alerts from multiple sensors into self-contained acoustic packages based on geographic and environmental constraints, request additional data from specific acoustic sensors, and run a localization algorithm to determine the location of the source of the acoustic event.

Abstract: A system and method for detecting songs in a continuous audio stream are disclosed. A detection server segments the continuous audio stream, and analyzes the audio stream to determine song candidates according to various processes disclosed herein. In one embodiment, the candidates are determined to be accurate when temporally ordered fingerprints exceed a predetermined threshold, adjacent audio stream segments are determined to have the same best song candidate, and the determined song detection has not been previously detected in the data stream within a predetermined period of time.

Abstract: A system and method for detecting songs in a continuous audio stream are disclosed. A detection server segments the continuous audio stream, and analyzes the audio stream to determine song candidates according to various processes disclosed herein. In one embodiment, the candidates are determined to be accurate when temporally ordered fingerprints exceed a predetermined threshold, adjacent audio stream segments are determined to have the same best song candidate, and the determined song detection has not been previously detected in the data stream within a predetermined period of time.

Abstract: Aspects of the present invention relate to methods and systems for high-accuracy differential tracking of global positioning system (GPS) receivers. In one embodiment, a network having multiple receivers is provided. The receivers are configured to communicate with each other. The receivers in the network are configured to measure raw satellite data, and to share the raw satellite data measured by each receiver. Each receiver is configured to process the measured raw satellite data with a Peak Ambiguity Function Value (AFV) Tracking Solution (PATS) to track relative motions of the neighboring receivers so as to derive relative location information for the plurality of receivers.