搜索资源列表
identified-in-set
- 基于MFCC参数和DTW算法的语音识别算法,对0-9这十个数字的中文发音进行识别。该程序对特定的五个人做集合内的识别,程序中已有语料。-The MFCC parameter and DTW algorithm-based speech recognition algorithm, the 0-9 ten digits Chinese pronunciation recognition. The program on five specific identification collection
identified-out-of-set
- 基于MFCC参数和DTW算法的语音识别算法,对0-9这十个数字的中文发音进行识别。该程序对特定的三个人的声音做训练,并用来识别这三个人之外的30个人的发音,即特定人的集合外的识别,程序中已有语料。-The MFCC parameter and DTW algorithm-based speech recognition algorithm, the 0-9 ten digits Chinese pronunciation recognition. Do training of the progr
dtw-recognizer
- 基于dtw的语音识别,使用的是mfcc特征参数。一个简单的demo-Dtw-based speech recognition, the use of is mfcc characteristic parameter. A simple demo
matlab-voice-match
- 语音识别,根据人的发音进行选择匹配,包括MFCC等多个matlab源文件-voice match
myhmm
- 数字0-9的语音识别算法,采用双门限端点检测算法,mfcc和lpcc相结合的特征参数提取。-Numbers 0-9 speech recognition algorithm, adopts double threshold endpoint detection algorithm, the combination of MFCC and LPCC feature parameter extraction.
chmm
- 数字0-9的语音识别实现,采用双门限端点检测算法,mfcc和lpcc相结合的特征参数提取,识别率较高。-Numbers 0-9 of speech recognition, adopts double threshold endpoint detection algorithm, the combination of MFCC and LPCC feature parameter extraction, the recognition rate is higher.
MFCCEX
- MFCC 特征提取。用于语音识别等方面,通过特征提取,然后再进行识别操作-MFCC feature ,using voice recognition
HMM
- HMM基于mfcc特征的语音识别,包括DTW算法演示、mfcc参数计算、端点检测等-HMM-based speech recognition feature mfcc
Neural-networks
- 神经网络进行语音识别:/enframe.m,该函数将输入向量分为固定长度固定重叠量的帧。/SampleCreate.m,将取所有音频的mfcc系数处理成神经网络函数所需的输入格式-Neural networks for speech recognition
CVadMfccDtw
- 进行端点检测,提取参数MFCC的基于动态时间规整的语音识别。-Endpoint detection, extraction of structured Speech recognition based on DTW which detects the endpoint and extracts MFCC as the parameter.
feature_selection_mfcc
- mfcc: 在语音识别中是一个非常重要的特征提取函数-mfcc: is a very important feature extraction function in speech recognition
MMFC_test1
- 在嵌入式系统上提取语言信号MFCC,是语音识别第一步。-MFCC extraction language signals on embedded systems, speech recognition is the first step.
voice-recognition
- 实现基于MFCC和HMM及Viterbi的语音识别系统,识别率可达到80 以上-MFCC and HMM-based speech recognition systems and Viterbi recognition rate can reach 80
great2
- mfcc代码 语音识别 matlab软件-matlab mfcc
yuyin
- 用DTW算法实现的孤立词语音识别,利用语音的mfcc特征进行识别,可识别0-9十个数。使用时请改相关路径.-DTW with isolated word speech recognition algorithm, using speech recognition mfcc characteristics can be identified 0-9 ten numbers. Please change the relative path when using
Desktop
- 语音采集,MFCC,滤波,采集等相关语音识别代码-matlab is good,matlab is good,matlab is good,matlab is good。
7102
- 基于匹配滤波器的语音识别。本程序接触匹配滤波对加噪语音进行匹配输出,使得信号的信噪比得到提升,送入后端DTW的语音识别系统,实验证明,本程序对语音提升有很大的帮助-A speech recoginiton base on the matched filter. this code will use matched filter and get speech SNR output enhanced. then we will extrace MFCC, send the feature to th
Dtw
- 这是一个基于DTW的语音识别的代码,里面包含端点检测和MFCC的提取。-This is a DTW-based speech recognition code, which contains end point detection and the extraction of MFCC.
HMM_VoiceRecognation
- 通过基于HMM的语音识别系统的基本结构,详细介绍了语音信号采集、预处理、MFCC特征参数提取、HMM训练和HMM识别等主要模块的基本原理 并针对实际应用中HMM存在的模型初始化和数据溢出等问题进行分析,引入了一些能提高系统性能的相应措施。-By the basic structure of HMM-based speech recognition system, details the basic principles of audio signal acquisition, preproces
m_files
- MFCC,Mel频率倒谱系数的缩写。Mel频率是基于人耳听觉特性提出来的,它与Hz频率成非线性对应关系。Mel频率倒谱系数(MFCC)则是利用它们之间的这种关系,计算得到的Hz频谱特征,MFCC已经广泛地应用在语音识别领域。-MFCC, Mel Frequency Cepstral Coefficients abbreviations. Mel frequency is proposed based on the human auditory characteristics. It comes