摘要
作为语音处理领域的主要技术之一,说话人识别以确认说话人身份为目标,在移动交互、身份验证、音频监控等领域有着广泛的应用前景。经过数十年的发展,说话人识别技术已经能够取得优秀的识别性能。本文将对说话人识别方法的研究现状进行总结与分析,介绍目前主流的说话人识别技术。
As one of the main technology of speech processing,speaker recognition aiming at speaker distinguishing,has a broad application prospect in the field of mobile interaction,authentication,audio monitor,and so on. After decades of development,speaker recognition has achieved a high accuracy. This paper will carry on the summary and analysis of speaker recognition,and introduces the current mainstream technology of speaker recognition.
出处
《智能计算机与应用》
2015年第5期92-94,97,共4页
Intelligent Computer and Applications
基金
国家自然科学基金(91120303)
关键词
说话人识别
特征提取
说话人模型
Speaker Recognition
Feature Extraction
Speaker Modeling
