Audio Indexing: What Has Been Accomplished and the Road Ahead

This paper presents an overview of audio indexing, which has emerged very recently as a research topic with the development of Internet. A lot of data, including audio data, are currently not indexed by web search engines, and audio indexing consists in finding good descriptors of audio documents which can be used as indexes for archiving and search. We discuss speech/music segmentation, language identification, speaker tracking and speaker indexing, and propose some research directions for other audio descriptors which have not been used in the framework of audio indexing, namely key sounds detection, keywords detection, and themes detection. We finally conclude this overview and give a few promising and key perspectives.