搜索资源列表
phoenix1.3.tar
- Phoenix is a speaker dependent (user trained) connected word recognition system. Phoenix is designed as a real-time recognition system in that recogniton takes place in parallel to utterance input and partial results are available before the en
PDFFILES
- 基于ARM7TDMI的SoC片内AC97模块和片外CODEC-UCB1400，采用ITU-T的G.721算法设计语音处理系统 提出一种基于低端RISC核的语音系统设计方案。该方案结合SoC的片内eSRAM模块进行性能优化；通过在流片后的实际样机上验证，编码速率为19.88 KB/s，解码速率为22.68 KB/s，达到了语音实时性要求。-ARM7TDMI-based SoC chip AC97 module and off-chip CODEC-mated 00. using the ITU-T
PPT-SoftwareEngineering
- 语音识别系统中前端PLP参数的提取和处理 孤立词识别系统中几种滤波器组的比较研究 基于Matlab命令字识别系统及实现 基于HTK的命令字识别系统及实现 基于HTK的数字串识别系统及实xian-Speech Recognition System front-end PLP parameters for the extraction and processing isolated word recognition sy
spec_subm
- 自适应滤波算法，可用于语音降噪等前端处理-adaptive filtering algorithms can be used for voice, and other front-end noise
fdpsola
- 语音合成程序！psalo频域基音同步叠加方法。它首先对原始语音信号进行短时频域变换，得到短时谱和短时谱包络。短时谱除以短时谱包络得到声源短时谱，对声源短时谱的实部和虚部分别进行线性插值，就可以达到改变语音信号基频的目的，然后再进行频域反变换，可得到变换后的短时语音信号。短时谱包络部分也可以独立改变，以达到改变音色的目的。-speech synthesis procedures! Psalo frequency domain pitch synchronous superposition meth
chinaword
- 汉字转声母完全源代码 -Chinese characters to the source code entirely consonant Chinese characters to the source code entirely consonant Chinese characters to End full source code
endpoint.rar
- 端点检测（短时能量，短时平均幅度，短时过零率）,short-term spectrum，spectrogram，End point detection
ubm.rar
- universal background model used in front end feature extraction in speech recognition.,universal background model used in front end feature extraction in speech recognition.
testdtw(zhu)
- function dist = dtw(t,r) n = size(t,1) m = size(r,1) 帧匹配距离矩阵 d = zeros(n,m) for i = 1:n for j = 1:m d(i,j) = sum((t(i,:)-r(j,:)).^2) end 累积距离矩阵 D = ones(n,m) * realmax D(1,1) = d(1,1) 动态规划 for i = 2:n
Endpoint-detection-of-speech-signal
- 语音信号的端点检测分析，有短时能量分析,短时过零率分析,和终点检测-Endpoint detection of speech signal, a short-term energy analysis, short-term rate of zero, and the end point detection
smartread_sdk
- 在你的软件中加入文本朗读,混读功能,支持中文,英文男女声混合朗读,免费提供多种语音库 ,在朗读文本时,可以自由设定朗读语音,语速,音量 并可以将文本朗读到Wave文件中去. 朗读时高亮显示文字功能,朗读是否结束的信息.-At the software you add text to read, read mixed function, support Chinese, English mixed male and female voices reading aloud, free databa
sesKirpma
- This function is remove the unvoice section from the voice. Which is end point detection by using rabiner algorithm.
entropy_t
- End Point Detection algorithm using Variable frame rate
VFR_him
- End Point Detection algorithm
ZCR_En
- End POint detection algorithm using Energy-ZCR
endPointDetect
- 简单的基于门限值的语音端点检测。先将数字化的语音信号封装成帧，利用最大的帧幅值乘以一个比例因子得到门限值-Simple threshold-based voice end point detection. First，framing the digital voice signal , then using the maximum amplitude to multiply a frame scale factor to get threshold
newvq
- this a speech recognition code based on vector qunatisation wid end point detection.-this is a speech recognition code based on vector qunatisation wid end point detection.
EndPointDetector
- End point detector Implementation of "An Algorithm for Determining the Endpoints of Isolated Utterances, L. R. Rabiner and M. R.Sambur
185_endpointdetector
- End point detector for speech
nlms-Double-end-detection
- 基于NLMS算法的回声消除，具有双端检测功能-Echo cancellation nlms Double-end detection