基于STM32的嵌入式语音识别设备 - 嵌入式综合 - 优领域 - 在优领域,找到您想要的! 关键词】STM32F103;语音识别;梅尔倒谱系数;动态时间弯折算法 [gap=746]Key words】STM32F103;speech recognition;MFCC;DTW
基于258个网页-相关网页
实验中,采用美尔倒谱系数(MFCC)作为话者语音特征参数。实验表明,基于LSSVM的话者识别比传统的SVM话者识别计算复杂度小,训练时间短,效率更高;同时,识别率也...
基于236个网页-相关网页
Pitch-MFCC 基于基音周期的MFCC特征参数
MFCC feature MFCC特征
Dynamic MFCC 动态MFCC
MFCC parameter MFCC参数
High order MFCC 高阶MFCC
MFCC feature weighting MFCC特征加权
Mapping the filtered MFCC to loudness the process of human perception is simulated.
将滤波后的参数映射为响度,由此模拟人的感知过程。
The experiment results show that the system built on DWT-MFC has better noise robustness than on LPCC and MFCC.
实验表明,与(LPCC)和(MFCC)参数相比,采用DWT-MFC参数使系统的噪声鲁棒性得到显著的提高。
During the experiment, MFCC (Mel Frequency Ceptral Coefficient) is adopted to speaker speech feature parameters.
实验中,采用美尔倒谱系数(MFCC)作为话者语音特征参数。
应用推荐