摘要
介绍一种基于浮点型数字信号处理器(TMS320C6713),并通过语音识别说话人身份的实用系统。为构建一个稳定实用的基于DSP说话人识别系统。以Mel倒谱系数作为特征参数,采用高斯混合模型作为识别模型,模型参数采用FLASH ROM存储,并实现自举运行。经过调试,实现了系统的自举运行,自举运行时可选择系统的训练和识别功能,并可方便地选择参加训练和识别的说话人,识别的范围为10人,识别的速度在3 s之内,准确率达98%以上。达到了系统设计的目的要求。与其他系统相比,该系统在实现算法上加以一定的改进,保证了识别率,并实现自举运行同时充分考虑可操作性,具有更大的实用价值。
A speaker recognition system based on speech and float point digital signal processor chip（TMS320C6713） is introduced. To design a practical speaker recognition system based on DSP, regarding Mel frequency cepstrum coefficient as the characteristic parameter,adopting the Gaussian mixture model, storing the parameter of mode in FLASH ROM and realizing bootstrap operation. By debugging,training and recognition are used. It can realize the speaker recognition of ten persons. The recognition accuracy of this system is over 98%, and the recognition time is about 3 s, the target is reached. Compared with other systems,this system has a higher practical value, because its method has been improved which ensures its recognition accuracy. It realizes bootstrap operation and can be operated easily.
出处
《现代电子技术》
2009年第22期203-206,209,共5页
Modern Electronics Technique
