搜索资源列表
Speechrecognitiontechnology
- 比较详尽的介绍了语音识别系统的实现过程，以及相关技术。 端点检测：基于短时能量和短时平均过零率的端点检测和基于倒谱特征的端点检测 特征参数提取：LPCC和MFCC 参数模板存储：HMM和N_Gram 识别阶段：DWT 各阶段的相关技术都给了详细的介绍，绝对是好东西！-More detailed introduction to the speech recognition system implementation p
Freq_Domain
- Transforming images from the spatial domain to frequency domain using FFT and DCT, also it includes transforming to the Cepstrum domain.
speech
- 这是一段语音识别的c++源程序，包括预处理，端点检测，线性倒谱系数，dtw算法模式匹配。-This is a speech recognition c++ source, including preprocessing, detection, linear cepstrum, dtw algorithm for pattern matching.
endpoint
- 这是一段关于语音处理与识别的程序，包括预处理，端点检测，线性倒谱系数求解，并运用dtw算法进行模式匹配。-This is a speech processing and recognition on the program, including pretreatment, endpoint detection, linear cepstrum solution, and the use of dtw algorithm for patt
wv2fftE
- 修改的倒谱处理语音的函数，将wav转为fft，采用了遮掩原理-Modified speech cepstrum processing function, fft into cepstrum by the cover principle
fft2ftftE
- 修改的倒谱处理语音的函数，将fft转为倒谱，采用了遮掩原理-Modify the function of speech cepstrum processing
dtw_MFCCs_full
- mel frequency cepstrum coeffcients
melcepst
- 求mel频率倒谱系数的程序，求的准确，时间相比其他程序多一点-Mel frequency cepstrum seeking the procedure, find the exact time a little more compared to other programs
meldaopu
- 关于mel倒谱系数提取的研究生论文，希望对各位初学者有很大的帮助-Mel cepstrum extraction on graduate thesis, you want to be very helpful for beginners
mfcc
- 语音识别mfcc美尔倒谱系数全过程的matlab程序，运行测试能出结果，希望对你们有用，实在没点数才把自己压箱底的东西拿出来,-Speech Recognition mfcc Mel cepstrum whole process of matlab program, run test can the result, I hope helpful for you, there is really no point only then th
ZCRa3
- about cepstrum of a speech signal
LPC_extractor
- 自己读取HTK源代码，从里面抠出来的一套LPC系数、LPCEPSTRA（LPC倒谱系数）代码。工程使用vc6.0。代码中附带了一个音频文件、一个和HCOPY相关的config文件，本人和HTK工具提取的代码一一对照过，提取结果毫无偏差。-HTK source code yourself to read, from the inside to pull out of a LPC coefficients, LPCEPSTRA (LPC c
gmfcc
- 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.
VQ-pattern-recognition
- VQ声纹识别算法和实验. 摘要：采用线性预测倒谱系数(1inear prediction cepstrum coefficient，LPCC)作为语音的特征参数，矢量量化(vector quantity，VQ)方法进行模式匹配，探讨声纹识别以实现身份认证，并对此识别方法进行了相关的实验．通过验证，这种方法可以区分不同的说话人，并且在做说话人辨认实验时可达到较高的识别率．-VQ pattern recognition algorith
voice
- 采用增减特征分量的方法研究了MFCC 各维倒谱分量对说话人识别和语音识别的贡献-Changes in characteristics of components using the method of the MFCC cepstrum of each dimensional component of the speaker recognition and speech recognition of the contribution
SR3
- 利用倒谱法对语音信号进行处理，其中语音信号可从本地上获取-Using cepstrum of speech signal processing, in which the speech signal can be obtained from the local
SRandRec
- 该源码为语音识别实验平台，算法为DTW+梅尔倒谱系数，并且包含录音函数，方便大家在此平台进行语音识别算法研究。-The source test platform for speech recognition, the algorithm for the DTW+ Mel cepstrum, and includes recording function, we facilitate a voice in this platform
chapter5_1
- 倒谱的matlab实现,先用cool edit 软件录制歌曲-the relization of cepstrum of Matlab