Search - MFCC

Search - MFCC - List

【Other】 TC_PLOT DL : 0: 本程序包含语音压缩和语音识别领域所需的LPCC，MFCC特征提取算法以及语音端点检测源码。在对语音数据进行特征提取前，可对语音数据进行16K到8K的降采样率处理，包含180阶FIR滤波器的频率压缩程序 -This procedure includes voice compression and voice recognition requirements in the area of the LPCC, MFCC feature extraction algorithm, as well as voice activity detection source. Voice data in the feature extraction before the voice data can be 16K to 8K sampling rate of the drop treatment, including the 180-order FIR filter frequency compression procedures
Update : 2024-04-27 Size : 1024 Publisher : lvjie
【Speech/Voice recognition/combine】 PCXLIB DL : 0: 本程序包含语音压缩和语音识别领域所需的LPCC，MFCC特征提取算法以及语音端点检测源码。-This procedure includes voice compression and voice recognition requirements in the area of the LPCC, MFCC feature extraction algorithm, as well as voice activity detection source.
Update : 2024-04-27 Size : 101376 Publisher : lvjie
【Audio program】 Audio1 DL : 0: 从麦克风读取数据，并用mfcc进行特征提取，最后通过dadboost分离器进行语音分离-Read data from the microphone and used MFCC feature extraction, and finally through the separator dadboost voice separation
Update : 2024-04-27 Size : 4073472 Publisher : gujunjun
【Speech/Voice recognition/combine】 GMMTRAIN DL : 0: 实现了从wave中读取数据，并通过mfcc提取特征系数。再通过分裂法聚类，最后使用EM算法建立GMM。-Realize the data read from the wave, and through MFCC feature extraction coefficient. Clustering through secession law, and finally the use of EM algorithm for the establishment of GMM.
Update : 2024-04-27 Size : 5120 Publisher : gujunjun
【Speech/Voice recognition/combine】 GMMTEST DL : 0: 从wave中读取数据，通过mfcc提取特征系数。从txt文件中读取基于GMM的分类器，最终识别为那种类型-Read data from the wave through the MFCC feature extraction coefficient. Txt file to read from the GMM-based classifier, and ultimately identified as the type
Update : 2024-04-27 Size : 4096 Publisher : gujunjun
【Speech/Voice recognition/combine】 speecher_identification DL : 0: 通过语音mfcc特征参数提取采用k均值算法实现说话人识别功能-Via voice MFCC feature extraction algorithm using k-means function of speaker recognition
Update : 2024-04-27 Size : 5120 Publisher :
【Speech/Voice recognition/combine】 speecharacter DL : 0: 自己编写的一段程序，可以对语音信号的六种主要特征参数进行提取。（其中MFCC需要调用melfb滤波器组。）-I have written for some procedures, voice signals can be the main features of the six parameters extracted. (Including MFCC filter banks melfb need to call.)
Update : 2024-04-27 Size : 1024 Publisher : 李云
【Speech/Voice recognition/combine】 SpeakerIdentifition DL : 0: 用MATLAB实现的基于MFCC特征和VQ量化的说话认识别程序-Realize using MATLAB-based features and MFCC quantization VQ other words awareness program
Update : 2024-04-27 Size : 168960 Publisher : joe
【Speech/Voice recognition/combine】 dsds DL : 0: 基于改进LPCC和MFCC的汉语耳语音识别,在MATLAB上设计出了基于LPCC和MFCC的汉语语音孤立词识别/-LPCC and MFCC Based on Improved Chinese ear speech recognition, in the MATLAB design based on the LPCC and MFCC Chinese isolated word speech recognition /
Update : 2024-04-27 Size : 344064 Publisher : chenfeng
【VC/MFC】 GeneralizedMFCCsforlarge-vocabulary DL : 0: 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
Update : 2024-04-27 Size : 165888 Publisher : xiang
【Speech/Voice recognition/combine】 MFCCmodel DL : 0: 求mfcc的模块的c文件！！mfcc模块在很多领域都可以用到-MFCC module for the c file! ! MFCC modules in many areas can be used
Update : 2024-04-27 Size : 1024 Publisher :
【Speech/Voice recognition/combine】 voiceidentificationlabview8.0 DL : 0: 这个我用ＬＡＢＶＩＥＷ８．０写的一个简单孤立词语音识别的程序，其中同过预处理，ＭＦＣＣ提取，和ＤＴＷ算法的比较，希望对大家有用-I used to write this LABVIEW8.0 a simple isolated word speech recognition procedures, which had the same pretreatment, MFCC extraction, and the DTW algorithm, in the hope that useful to everybody
Update : 2024-04-27 Size : 229376 Publisher : hu
【Speech/Voice recognition/combine】 textindependentspeakerrecognition DL : 0: 这个我用matlab写的一个简单孤立词语音识别的程序，其中同过预处理，ＭＦＣＣ提取，和ＤＴＷ算法的比较，如果大家愿意，还可以用这个和ＬＡＢＶＩＥＷ联合编程-Matlab write this I used a simple isolated word speech recognition procedures, which had the same pretreatment, MFCC extraction, and the DTW algorithm, if everyone is willing, but also can use this joint programming and LABVIEW
Update : 2024-04-27 Size : 3072 Publisher : hu
【Speech/Voice recognition/combine】 MFCC_matlab DL : 0: mfcc-matlab,用matlab实现语音信号特征识别的mfcc方法-mfcc-matlab, speech signal using matlab realize the MFCC feature recognition method
Update : 2024-04-27 Size : 450560 Publisher :
【VC/MFC】 mfcc DL : 0: 对语音信号的进行分帧，短时能量计算，过零检测计算，设置门限-Voice signal on the conduct of sub-frame, short-time energy calculation, zero-crossing detection, the set threshold
Update : 2024-04-27 Size : 1024 Publisher : liguang
【Speech/Voice recognition/combine】 fengcengmfcc DL : 0: 把声音数据先进行小波分层然后各层进行mfcc系数提取-Voice data first and then layered on each floor to carry out wavelet coefficients MFCC extraction
Update : 2024-04-27 Size : 1024 Publisher : 赵欣
【Speech/Voice recognition/combine】 mfcc DL : 0: 语音处理中用于特征提取，mel倒谱系数法可以反映语音的动态特征。-Voice processing for feature extraction, mel cepstral coefficients method can reflect the dynamic characteristics of voice.
Update : 2024-04-27 Size : 4096 Publisher : 方方
【matlab】 matlabtosolve DL : 1: 基于MATLAB实现的说话人识别程序，分别用bp、pnn、som、rbf、lvq等算法，对语音文件进行训练和测试，效果不错。~..~ 下面说明一下bprengong程序：数据分别用来训练和测试两部分。具体程序分为两部分，第一部分为：计算识别模型变量v是mfcc处理以后的矢量。因为数据可能长短不一，所以放在同一进行截取。p的每一行代表一个语音数据（共15个）。变量Pr为每一行的最大最小值。变量T为目标值。输出神经元个数为15。在训练阶段，如果用于训练的输入训练样本的类别标号为i（即语音数据的标号），则训练时设第i个节点的期望输出设为1。其余节点期望输出均为0。在识别时，当一个未知类别的样本作用到输入端时，考查各输出节点的输出，并将这个样本的类别判定为输出值最大的那个节点对应的类别。 -err
Update : 2024-04-27 Size : 658432 Publisher : wang
【Other】 mfcc1 DL : 0: matlab中MFCC提取，在6.5中编译通过！-matlab in MFCC extraction, in the 6.5 compiler through!
Update : 2024-04-27 Size : 1024 Publisher : 陈
【Speech/Voice recognition/combine】 MFCCs DL : 0: 提取MFCC的matlab代码，用于提取MFCC-梅尔倒普系数-MFCC extraction of matlab code, for the extraction of MFCC-Mel Pu inverted coefficient
Update : 2024-04-27 Size : 2048 Publisher : DK

« 1 2 3 4 5 6 78 9 10 11 12 ... 41 »