Description: 本程序是提取语音MFCC参数的必经步骤，是求出mel三角滤波器器组的参数，网上只有matlab程序，没有C程序，本人花费两个星期的时间才转换成功，经DSP 的CCS环境调试成功。-This procedure is the extraction of voice MFCC parameters necessary step is to derive the triangular mel filter device group parameters, on-line only matlab procedures, no C program, I spent two weeks time to convert the success of the CCS environment by DSP debugging success. Platform: |
Size: 1024 |
Author:何正明 |
Hits:
Description: 基于不变集多小波的语音特征参数提取研究 用小波变换替代傅立叶变换和梅尔滤波-Based on the invariant set Multiwavelet voice characteristic parameter extraction for research of wavelet transform and Fourier transform alternative Mel filter Platform: |
Size: 1161216 |
Author:王岐学 |
Hits:
Description: 自己编写的求mel三角滤波器系数的程序，比matlab自带程序容易理解，帮助大家理解mel三角滤波器-I have written for triangular mel filter coefficients procedures, than matlab own procedures easy to understand and help us to understand the triangular mel filter Platform: |
Size: 1024 |
Author:cao |
Hits:
Description: 对录音信号集 中的某一语音，利用BATLAB设计一美尔例谱算法，并实现。
取信号集 中的一个语音信号：“xxxxxx”，将它作为输入的语音信号来为设计一个美尔倒谱算法，在该算法中，主要设计了以下环节：
1.读入一个语音信号；2.对这个信号归一化；3.对归一化的信号进行加窗处理（这里的矩形窗长度必须为257，重帧长64）；4.进行预加重处理，即通过一个高通滤波器： ；5进行512点的FFT；6.分别取模平方得到功率谱；7.在设计的mel滤波器组中，我采用了25个带通滤波器；8.将得到的功率谱信号通过mel滤波器组，得到相应的25个功率值；9.对这些功率值取自然对数；10.对这些值取离散作弦变换；11.将得到的值去掉直流分量，取其它值作为MFCC参数。
-Concentrated on recording a voice signal, using BATLAB designed Mayer cases spectral algorithm, and implementation.
Get a voice signal signal focus: "xxxxxx", will it as input for the design of a voice signal to Mel Cepstrum algorithm in the algorithm, the main design of the following links:
1. Read a speech signal 2. On the signal normalized 3. Of the normalized windowed signal processing (here, rectangular window length must be 257, re-frame size 64) 4. For Pre-emphasis processing through a high-pass filter: 5 for 512 points of FFT 6. modulo square were obtained spectrum 7. in the design of mel filter banks, I use a 25 band-pass filter 8 . will be the power spectrum signal by mel filter bank, corresponding to the 25 power values 9. on the power to take the natural logarithm value 10. to take these values as strings of discrete transform 11. will be of value to out DC component, to take other values as MFCC parameters. Platform: |
Size: 13312 |
Author:赵欣 |
Hits:
Description: it is a collection of matlab program.
1.to find the euclidian distance
2.to create mel frequency filter bank
3. Platform: |
Size: 2048 |
Author:sandeep |
Hits:
Description: 于市售 STM32 开发板上实现特定人语音识别处理项目。识别流程是：预滤波、ADC、分帧、端点检测、预加重、加窗、特征提取、特征匹配。端点检测(VAD)采用短时幅度和短时过零率相结合。检测出有效语音后，根据人耳听觉感知特性,计算每帧语音的 Mel 频率倒谱系数(MFCC)。然后采用动态时间弯折(DTW)算法与特征模板相匹配,最终输出识别结果。先用Matlab对上述算法进行仿真，经数次试验求得算法内所需各系数的最优值。而后将算法移植到 STM32 开发板上，移植过程中根据 STM32 上存储空间相对较小、计算能力也相对较弱的实际情况，对算法进行优化。最终完成于 STM32 微处理器上的特定人语音识别系统。-Implement speech recognition processing project in commercially available STM32 development board. Identification is the process: pre-filter, ADC, framing, endpoint detection, pre-emphasis, windowing, feature extraction, feature matching. Endpoint detection (VAD) short-time amplitude and short-term zero rate combined. After detecting an effective voice, according to the characteristics of human auditory perception, calculated for each frame of speech Mel Frequency Cepstral Coefficients (MFCC). Then dynamic time warping (DTW) algorithm and feature template matches the final output recognition result. First with Matlab simulation algorithm described above, after several trials to get the optimal value of each coefficient within the desired algorithm. The algorithm will migrate to STM32 development board, the porting process according to the STM32 relatively small storage space, computing power is relatively weak situation of the optimization algorithm. Finally completed on the STM32 micr Platform: |
Size: 325632 |
Author:Chenkly |
Hits:
Description: matlab实现语音信号基于mel滤波器的端点检测，并应用于一个语音文件上。-Matlab to achieve voice signal based on mel filter endpoint detection, and applied to a voice file. Platform: |
Size: 177152 |
Author:宋飞 |
Hits:
Search - mel filter matlab