基于FPGA的语音特征参数提取模块的设计  

Design of Speech Feature Parameter Extraction Module Based on FPGA

作　　者：马智愚 MA Zhi-yu(School of Physics and Information Engineering,Fuzhou University,Fuzhou 350116,China)

机构地区：[1]福州大学物理与信息工程学院

出　　处：《通信电源技术》2019年第6期43-44,48,共3页Telecom Power Technology

摘　　要：基于FPGA设计了一种语音特征参数提取模块。针对生活中孤立词识别的应用场景,采用了最常用的MFCC特征参数。利用FPGA上丰富的IP资源和查找表结构,实现了MFCC特征参数提取独立模块的设计,提高了运算速度。采用了蜂鸟e203作为MCU控制特征提取模块。仿真结果表明,该特征参数提取模块运算速度快,误差在1%以内,满足实时处理的应用要求。Based on FPGA,a speech feature parameter extraction module is designed. The most commonly used MFCC feature parameters were selected for the application scenarios of isolated word recognition in life. Using the rich IP resources and lookup table structure on the FPGA,the independent module design of MFCC feature extraction is realized,which improves the operation speed. Hummingbird e203 is adopted as the MCU control feature extraction module. The simulation results show that the feature parameter extraction module has a fast operation speed and the error is less than 1%,which meets the application requirements of real-time processing.

关 键 词：FPGA 语音特征参数 MFCC MCU RISV-V 

分 类 号：TN912.34[电子电信—通信与信息系统] TN791[电子电信—信息与通信工程]