搜索资源列表
语音语谱图与基频
- 编译时需要intel C++编译器支持,程序主要功能显示语音波形,画出窄带语谱图,以及语音基频变化曲线-need intel compiler C compiler support, principally voice waveform display function, he painted the phrase narrowband spectrum, and the voice-frequency curve
dtw-new
- DTW (Dynamic Time Warping)源程序，广泛应用于语音识别等领域，可以用于相似曲线的对齐。（用winrar进行解压）-DTW (Dynamic Time Warping) source. widely used in areas such as speech recognition, which can be used similar to the curve alignment. (Using WinRAR for decompression)
lsm_switchfield
- 基于LMS算法的变换域的源程序，里面给出了学习曲线，迭代后的输出曲线-LMS algorithm based on the Domain source, which is a learning curve, the output iterative curve
lsm_filter
- 基于LMS算法的滤波型算法的源代码，包含有对学习曲线的刻画。迭代后的输出曲线。-LMS algorithm based on the filtering algorithm source code contains the learning curve is given. Iterative the output curve.
SPECTRUM_LMS
- 1、文件夹中包含了经典功率谱估计和自适应均衡算法两个实验的所有程序。 2、R.m、LMS.m、LMSmain.m为自适应均衡算法的程序： R.m用来计算输入信号的自相关矩阵及其特征值； LMS.m为时域LMS算法，用统计的方法仿真得出不同信道参数和不同步长下的学习曲线； LMSmain.m为实验主程序，按照实验要求中的具体数据得到实验结果和曲线。 3、functionx.m、fzhouqitu.m、spectrum.m、bt.m、bart_lett.m、welch.m、SPE
DETware_v2[1].1.tar
- 求误识率——拒识率曲线（DET曲线） 常应用于说话人识别-seek error rate -- reject rate curve (DET curve) often used in speaker recognition
det(C++)
- 计算误识率——拒识率曲线（VC++） 应用于说话人识别系统中。-calculation error rate -- reject rate curve (VC) for speaker recognition system.
btlbandstop
- 巴特沃特带阻滤波器的设计，返回分子分母多项式系数，还可以作出增益曲线，以及求出相位响应以及群延时响应-Batewote band stop filter design, the return of molecular denominator polynomial coefficients, can gain curve, and the calculated phase response and group delay response
lms
- 再传一个LMS的小程序，有三个图，System output，Error curve，Comparison of the actual weights and the estimated weights
eqber_adaptive
- This scr ipt runs a simulation loop for either a linear or a DFE equalizer. It uses the RLS algorithm to initially set the weights, then uses LMS thereafter to minimize execution time. It plots the equalized signal spectrum, then generates and plot
Sound_Viewer
- 绘制声音波形，可用于声音波形曲线的实时绘制。-Mapping sound waves, it can be used for real-time sound waves rendering curve.
LPC
- 基于线性预测系数(LPC)的语音信号重构。给出了完整的LPC matlab程序，包括语音信号采集，LP预测系数，阶数的选择以及预测结果误差曲线。（很好用）-Based on the linear prediction coefficient (LPC) voice signal reconstruction. Given a complete LPC matlab procedures, including voice signal acquisition, LP prediction coef
Tone-Recognition
- 一种通过线性规划和曲线拟合，对汉语言进行声调识别的方法，准确率98.9 -One kind of curve fitting by linear programming and, for tone recognition of Chinese language and methods, accuracy 98.9
1
- LMS 算法源程序，绘制性能曲线图，误差性能曲线-LMS algorithm source code, rendering the performance curves, the error performance curve
yuyinxinhaolianghua
- 采用矢量量化对语音信号量化，并与标量量化对比分析，绘制了语音信号的概率密度曲线-The use of vector quantization for speech signal quantization and scalar quantization and comparative analysis, rendering the speech signal probability density curve
VBwav
- 用vb软件对WAV格式的音频，进行详细分析，并绘制曲线图-WAV format using vb software audio to conduct a detailed analysis and draw curve
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
yuyinjipin
- 加入3点或5点中值平滑处理后再绘制上述基频曲线与未平滑曲线比较，观测完整一段话音的基频包络变化情况-Add to 3:00 or 5:00 in the value of the smoothing then draw the base frequency curve is not a smooth curve compared with the observed period of complete voice baseband envelope changes
matlab
- 1. 给一段原始的语音信号（可以是自己录制的一段语音），加上一频率为3.8kHz的高频余弦噪声和频率为3.6kHz的高频正弦噪声（幅度自己可以选择），用窗函数设计一滤波器（要求最小阻带衰减为50dB）对加噪后的语音信号进行滤波，画出滤波器的频率响应曲线，画出滤波前后的时域图和频谱图。 需要用到的函数： fir1 用窗函数设计FIR滤波器的函数 2. 用GUI设计一界面（如图1所示）完成如下功能： 1） 输入一语音信号，画出语音信号的时域图和频谱图； 2） 对语音信号加噪处理，
roc2
- roc2.m computes the TAR and FAR by constructing a ROC curve the input genuine and imposter pairs. Faster and simpler matlab implementation.-roc2.m computes the TAR and FAR by constructing a ROC curve the input genuine and imposter pairs. Faster and