摘要
机器听觉包括三大研究领域:语音信号处理与识别、一般音频信号分析、基于内容的音乐信号分析.其中,语音信号处理与识别早已成为一个传统的研究热点.随着信息科学与技术的迅速发展,基于内容的音频与音乐信号分析也逐渐成为一个新的研究热点,近几年来取得了大量研究成果.文章将对1990年以后该领域上所取得的研究成果进行综述,包括基于内容的音频或音乐信号自动分类、分割、检索以及音乐作品自动分析等内容.
Machine hearing includes three fields: Speech signal processing and recognition, general audio signal processing, and content-based music analysis. Speech signal processing and recognition has been a traditional research field for many years. There are many summarizing works about it. With the rapid progress of the information science and techniques, the content-based music analysis, and general audio signal processing have gradually become hotspots of research in the fields of pattern recognition, and multimedia data processing. Lots of research productions have been reported in recent years, but summarizing works are lacked. This paper gives a detailed review of content-based audio and music analysis, mainly aiming at the latest progress.
出处
《计算机学报》
EI
CSCD
北大核心
2007年第5期712-728,共17页
Chinese Journal of Computers
基金
国家自然科学基金(60573060)资助.
关键词
音乐分类
识别
分割
检索
音乐分析
自动摘要
音频信号处理
模式识别
music classification
recognition
segmentation
retrieval
analysis of music
automatic music summary
audio processing
pattern recognition