说话人识别技术以其方便、经济和易于被接受等特点日益成为人们生活和工作中重要且普及的用户身份验证方式,但是在嵌入式领域的应用中,现有算法难以很好地满足实时性的要求。该文研究了应用于语音识别的非线性分块算法,将其思想加以改进,以逐块对比的识别方式用于嵌入式的文本相关说话人识别,与传统的基于动态时间弯折的方法相比,在实时性方面取得了良好的实用效果。
Abstract
The speaker recognition technology is an important and popular user authentication method in daily life due to its convenience, economy, and easy-to-acceptance. However the current algorithms cannot meet the real-time requirements in embedded applications. Based on the Non-Linear Partition (NLP) algorithms used in speech recognition, a novel algorithm is proposed and applied to the embedded Text-Dependent Speaker Recognition. Compared with the traditional Dynamic Time Warping (DTW) based algorithms, it achieves a good practical result in terms of real time performance.
Key wordsspeaker recognition; Text-Dependent; embedded application; Non-Linear Partition
关键词
说话人识别 /
文本相关 /
嵌入式 /
非线性分块
{{custom_keyword}} /
Key words
speaker recognition /
Text-Dependent /
embedded application /
Non-Linear Partition
/
/
/
/
/
/
/
/
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 蒋力. 基于概率统计模型的非特定人语音识别方法与系统的研究[D]. 北京: 清华大学,1989.11.
[2] 郑方.非特定人连续数字识别方法与汉语语音数据库的研究[D].北京: 清华大学,1992.
[3] 郑方,吴文虎,方棣棠. CDCPM 及其在语音识别中的应用[J]. 软件学报, 1996, 7: 69-75.
[4] Thomas Fang Zheng, Chai Haixin, Shi Zhijie. A real-world speech recognition system based on CDCPMs[C]//Int’l Conf. on Computer Processing of Oriental Languages (ICCPOL’97), 1997, 1: 204-207.
[5] Reynolds A. Reynolds. Speaker identification and verification using Guassian mixture speaker models[C]//Speech Communication. 1995, 17(1-2): 91-108.
[6] N. Z. Tisby. On the application of mixture AR hidden Markov models to text independent speaker recognition[C]//IEEE Trans. Signal Processing, March 1991, 39(3): 563-570.
[7] Zheng, F., Wu, W.-H., Fang, L.-T., A Log-Index Weight Cepstral Distance Measure for Speech Recognition [J]. J. of Computer Science and Technology (JCST), 1997, 12(2): 177-184.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(588 KB)
