Sound spotting: an approach to content-based sound retrieval

摘要: We present an approach to content-based sound retrieval using auditory models, self-organizing neural networks, and string matching techniques. It addresses the issues of spotting perceptually similar occurrences a particular event in audio document. After introducing problem basic we describe individual stages system give references additional literature. The third section paper summarizes preliminary experiments involving models maps carried out so far, final discussion reflects on overall concept suggests further directions.