Location:
Search - MEL recognition
Search list
Description: 一段数字读音转MEL系数的源码，相信在语音识别特征提取中可以有和大的用处-a digital switch pronunciation MEL coefficient of the source code, I believe the speech recognition feature extraction can be a useful and
Platform: |
Size: 3072 |
Author: 曹永新 |
Hits:
Description: 本程序是用MATLAB编写的孤立词的语音识别的程序，包含mel倒谱分析以及单个词的语音识别。-This procedure is used to prepare MATLAB isolated word speech recognition procedures, including mel cepstrum analysis, and single-word speech recognition.
Platform: |
Size: 6144 |
Author: 刘永哲 |
Hits:
Description: 说话人识别程序特征参数为MEL倒谱，模型为VQ量化-Speaker recognition process characteristic parameters for the MEL cepstrum, models for the VQ quantization
Platform: |
Size: 5120 |
Author: joe |
Hits:
Description: Generalized Mel frequency cepstral coefficients for large-vocabulary Speaker-Independent Continuous-Speech Recognition 关于MFCC算法的很好的英语文章-Generalized Mel frequency cepstral coefficients for large-vocabulary Speaker-Independent Continuous-Speech Recognition on the MFCC algorithm is a very good article in English
Platform: |
Size: 165888 |
Author: xiang |
Hits:
Description: mfcc mel倒谱系数学习。适合语音识别参数的学习。-mfcc mel cepstral coefficient learning. Parameters for speech recognition learning.
Platform: |
Size: 1024 |
Author: 沈立金 |
Hits:
Description: 建立了一种基于自组织神经网络的语音识别系统。对语音信号进行了预处理, 提取了语音信号的线性预测系数、线性预测倒谱系数和Mel 倒谱特征系数, 建立了基于自组织神经网络的识别判决模型.-Established a self-organizing neural network-based speech recognition system. Carried out on the speech signal pre-processing, extraction of the speech signal linear prediction coefficient, linear prediction cepstral coefficients and the characteristics of Mel cepstrum coefficient, based on self-organizing neural network model of identification judgments.
Platform: |
Size: 114688 |
Author: 张小天 |
Hits:
Description: 基于Mel倒谱特征和RBF网络的孤立词语音识别方法-Mel-based cepstral features and RBF networks isolated word speech recognition method
Platform: |
Size: 239616 |
Author: yuanjiaxing |
Hits:
Description: In this project we have processed the speech signal with the help of the DIGITAL SIGNAL PROCESSING techniques. The speech signal is given as the input will be verified using speech recognition technique using matlab. We have used Mel Frequency Cepstral Coefficient (MFCC) along with Vector Quantization (VQLBG) and Euclidean Distance to identify different characters. Based on the results, data was send to Parallel Printer Port of the computer & using relay different devices will be controlled.
Platform: |
Size: 2048 |
Author: SimonKap22 |
Hits:
Description: MATLAB下使用Mel倒谱特征进行说话人识别源代码-MATLAB using Mel Cepstrum for Speaker Recognition Source Code
Platform: |
Size: 756736 |
Author: 李宁 |
Hits:
Description: Speech Recognition using MEL cepstral Coefficients
Platform: |
Size: 3072 |
Author: ab.m |
Hits:
Description: melfiltter function use for speech recognition and have mel filter bank
Platform: |
Size: 2048 |
Author: nill |
Hits:
Description: 语音识别的特征参数提取算法——Mel倒谱参数提取（MFCC）可以作为语音识别特征参数。-Speech recognition feature extraction algorithm- Mel cepstrum extraction (MFCC) feature parameters as speech recognition.
Platform: |
Size: 1024 |
Author: 林锡海 |
Hits:
Description: 语音识别系统，包括预处理，汉明窗，梅尔频率倒谱率，离散余弦变换，前置滤波器组，对数能量，滤波器组，基本的滤波器组，dtw-speech recognition system，including Pretreatment, Hamming window, Mel frequency cepstrum rate, discrete cosine transform, pre-filter, log energy, filter, basic filter，dtw
Platform: |
Size: 6144 |
Author: 刘文龙 |
Hits:
Description: 该程序适用于语音识别系统，其用G语言实现了美尔倒谱的labview程序，非常推荐-This procedure applies to speech recognition systems, with the G language of Simmel cepstrum labview program, highly recommended
Platform: |
Size: 4096 |
Author: sun kai |
Hits:
Description: Title: "Voice Recognition and Identification system".
Mainly involves:
1: Human speaker recognition
2: Technical data of samples
3: linear and logarithmic power spectrum plot
4: Plots for different values for N
5: Mel Space
6: Modified spectrum
7: 2D plot of accustic vectors
8: Plot of the 2D trained VQ codewords
9: Recognition rate of the computer
and so on-Title: "Voice Recognition and Identification system".
Mainly involves:
1: Human speaker recognition
2: Technical data of samples
3: linear and logarithmic power spectrum plot
4: Plots for different values for N
5: Mel Space
6: Modified spectrum
7: 2D plot of accustic vectors
8: Plot of the 2D trained VQ codewords
9: Recognition rate of the computer
and so on.....
Platform: |
Size: 309248 |
Author: atish |
Hits:
Description: Voice Recognition Algorithms using Mel
Frequency Cepstral Coefficient (MFCC) and
Dynamic Time Warping (DTW) Techniques
Platform: |
Size: 466944 |
Author: Fatih |
Hits:
Description: mfcc用于求取训练样本的特征值，其需要melbankm和enframe两个程序。
enframe用于将语音分帧，melbankm用于产生mel三角滤波器组，vqlbg用于获取说话人码书，disteu程序用于计算两个矩阵间的距离，-mfcc strike eigenvalues for the training sample, which requires melbankm and enframe two procedures. enframe for the voice of the frame, melbankm used to produce the triangular mel filter bank, vqlbg codebook is used to get people talking, disteu procedures used to calculate the distance between two matrices,
Platform: |
Size: 4096 |
Author: 赵岩 |
Hits:
Description: MFCC参数是基于人的听觉特性利用人听觉的屏蔽效应，在Mel标度频率域提取出来的倒谱特征参数。-MFCC parameters is based on human auditory characteristics using human auditory masking effect, in Mel scale frequency domain parameters of cepstrum.
Platform: |
Size: 4096 |
Author: 徐金 |
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: 基于动态时间规整的孤立词语音识别，用梅尔倒谱系数作为识别特征。-Based on dynamic time warping of isolated word speech recognition, using Mel s coefficient as the recognition feature.
Platform: |
Size: 1476608 |
Author: 裴安山 |
Hits: