Audio signal recognition for speech, music, and environmental sounds

摘要

Human listeners are very good at all kinds of sound detection and identification tasks, from understanding heavily accented speech to noticing a ringing phone underneath music playing at full blast. Efforts to duplicate these abilities on computer have been particularly intense in the area of speech recognition, and it is instructive to review which approaches have proved most powerful, and which major problems still remain. The features and models developed for speech have found applications in other audio recognition tasks, including musical signal analysis, and the problems of analyzing the general ‘‘ambient’’ audio that might be encountered by an auditorily endowed robot. This talk will briefly review statistical pattern recognition for audio signals, giving examples in several of these domains. Particular emphasis will be given to common aspects and lessons learned.