搜索资源列表
Mmse84
- 利用Y.Ephraim提出的短时谱幅值最小均方误差法估算的语音增强法，附有相应程序和文献。-Y. Ephraim proposed the use of short-term amplitude spectrum MMSE Speech Enhancement Estimating law, with the corresponding procedures and documentation.
Mmse85
- 利用Y.Ephraim提出的对数谱幅值最小均方误差法估算的语音增强法，附有相应程序和文献。-Y. Ephraim proposed use of spectrum amplitude MMSE Speech Enhancement Estimating law, with the corresponding procedures and documentation.
ccb
- 基于分裂法的lbg算法，用分裂质心的方法进行，直到达到码字数量为止。-Secession Law of the LBG-based algorithms, used to split the centroid method, until it reaches the number of code words so far.
alawvoice
- 用TSM320C5402芯片基于A律压缩的语音压缩存储与回放-With chip-based A law TSM320C5402 compressed storage and playback voice compression
wavelet
- 基于小波变换法的基音周期检测 比较基础 大家借鉴看看吧 -Based on Wavelet Transform Pitch Detection law basis of comparison to see if you learn from everyone
MySR
- 这是一个的matlab的对语音处理文件。、 包括录音，MFCC特征，VQLBG法的库的形成，与非特定人的识别问题。-This is one of the matlab files for voice processing. , Including the recording, MFCC characteristics, VQLBG law, the formation of the Treasury, with non-specific identification of people.
DTWspeech
- 本 文 首先 介绍了语音识别的研究和发展状况，然后循着语音识别系统的 处理过程，介绍了语音识别的各个步骤，并对每个步骤可用的几种方法在实 验基础上进行了分析对比。研究了语音信号的预处理和特征参数提取，包括 语音信号的数字化、分帧加窗、预加重滤波、端点检测及时域特征向量和变 换域特征向量.其中端点检测采用双门限法.通过实验比对特征参数的选取， 采用12阶线性预测倒谱系数作为识别参数。详细分析了特定人孤立词识别算 法，选定动态时间弯折为识别算法，并重点介绍其设计实现。 在
jiyinzhouqijiance
- 一些关于语音基音周期检测的文章，包括多种测量方法，如小波变换法，相关法，还有多种改进方法的探讨。-Some information about Pitch detection of articles, including a variety of measurement methods, such as the wavelet transform method, the relevant law, there are many improved methods explored.
dtw
- 本系统是一个在多媒体PC 上实现的孤立词识别系统, 它提取语音的线性预测系数作为特征参数, 并采用Itaku ra 失真测度计算帧间距离, 在识别上则使用了动态时轴弯曲(DTW ) 进行时间匹配。本系统对一般的DTW 法作了改进, 即通过放宽端点限制以得到更好的语音匹配, 克服了一般DTW 法要求语音首尾严格对齐而造成的弊病, 降低了语音端点检测的精度要求。-This system is implemented on a multimedia PC isolated word recogniti
PCM-A-U-law
- 实现PCM语音数据流压缩，通过该压缩算法可以实现a/u law-PCM voice data stream to achieve compression, the compression algorithm can be achieved by a/u law
G711
- G.711标准A律和u律8kHz采样16比特数字语音编码的C语言实现-Standard G.711 A-law and u law 8kHz sampling 16-bit digital speech coding in C language
CS-yuyin
- 自己搜集的关于语音方面的论文，CS，压缩感知，是最近的热门，打破了采样定律，结合CS的语音论文，这里给出，很全面。-His collection of papers about speech, CS, compressed sensing, is recently popular, breaking the law of sampling, combined with the voice of the CS papers, shown here, is very comprehensive.
pcm2wav
- PCM编码(A律或U律)格式文件转换成WAV格式文件的VC6.0项目。-A VC6.0 project to covert PCM format(a-law/u-law) to WAV format.
pcm-mix
- 将2路PCM编码语音文件(A律或U律)合并成一路PCM编码语音文件的VC6.0工程。-Mixing 2 way PCM format file(a-law or u-law) into one PCM format file.
yuyinxuebo
- 利用三电平中心削波自相关法实现清、浊音判定，并提取一段话音的基频参数，绘制基频曲线，并将该参数曲线合并到前面提取的短时过零率和短时能量参数曲线图中-Using a three-level center clipping from the relevant law to achieve clear, voiced determination, and extract some of the fundamental parameters of the voice, drawing the funda
Signal_Quantization
- 使用MATLAB， 实现对一个余弦信号的均匀量化和A律非均匀量化， 并将结果输出在图形界面上。- Using MATLAB, Cosine signals to achieve a uniform quantization and A-law non-uniform quantization, And outputs the results in a graphical interface.
pcm
- 对语音信号进行脉冲编码调制，采用A律13折线-Voice signal pulse coding modulation, using A Law 13 polyline