一种应用于视频内容分析的话者辨识系统
首发时间:2008-02-19
摘要:音频分析技术在视频内容辅助分析中的应用日益成为研究的热点。本文提出了一种应用于视频内容分析的话者辨识系统,该系统的主要组成部分包括:特征提取、基于支持向量基(SVM)分类器的音频分类与分割、基于谱聚类算法的语音聚类和基于高斯混合模型(GMM)的话者辨识。实验数据来源于新闻视频、访谈视频和电影视频。实验结果证明了系统的有效性。
关键词: 话者辨识 视频内容分析 音频分类与分割 谱聚类 高斯混合模型
For information in English, please click here
A Speaker Identification System for Video Content Analysis
Abstract:Recently, more literatures proposed to apply audio content analysis techniques in content-based video parsing. This paper presents our current works on a speaker identification system for video content analysis, which consists of such basic parts: feature extraction, audio classification and segmentation using rule and Support Vector Machine(SVM) based classifier; speech clustering using spectral clustering technique and speaker identification based on Gaussian Mixture Model(GMM). Experiments are carried on a database extracted from news, conversation and movie videos. The obtained results confirm the validity of the proposed system architecture.
基金:
论文图表:
引用
No.1871819890112033****
同行评议
勘误表
一种应用于视频内容分析的话者辨识系统
评论
全部评论0/1000