数据采集与处理2016，Vol.31Issue(5)：1020-1027,8.DOI:10.16337/j.1004-9037.2016.05.020
一种基于指纹因子的鲁棒音频检索方法
Robust Audio Retrieval Method Based on Fingerprint Factors
摘要
Abstract
A noise-robust fingerprint-factor-based audio feature and a semi-supervised audio dictionary training algorithm are proposed to fill up the deficiency caused by noise in content-based audio retrieval. The proposed method extracts audio fingerprint from Mel spectra and utilizes non-negative matrix factori-zation to factorize fingerprint into noise-robust spectral factor and temporal factor as features.Also an semi-supervised audio dictionary training algorithm is proposed.It uses an audio effect set to calculate the distribution of basic sound effects as initialized dictionary.The quantization is conducted while the dic-tionary is dynamically updated at the same time to better characterize data.The experimental results show that under low signal-to-noise ratio (SNR),the proposed method significantly improves the average precision compared with other algorithms.关键词
音频检索/音频指纹/非负矩阵分解/音频字典/倒排索引Key words
audio retrieval/audio fingerprint/non-negative matrix factorization/audio dictionary/invert-ed index分类
信息技术与安全科学引用本文复制引用
林静,杨继臣,张雪源,李新超..一种基于指纹因子的鲁棒音频检索方法[J].数据采集与处理,2016,31(5):1020-1027,8.基金项目
国家自然科学基金(61301300)资助项目。 （61301300）
