Description: 一个什么都能做的语音处理软件，Manual segmentation of speech waveforms - creates label files which can be used to train speech recognition systems
Waveform editing - cutting, copying or pasting speech segments
Formant analysis - displays formant tracks of F1, F2 and F3
Pitch analysis
Filter tool - filters speech signal at cutoff frequencies specified by the user
Comparison tool - compares two waveforms using several spectral distance measures
Speech degradation -can do what a voice processing software, Manual segmentation of speech waveforms - crea tes label files which can be used to train speech recognition systems Waveform editing - cuttin g, copying or pasting speech segments Formant ana P <0.05-displays formant tracks of F1, F2 and F3 Pitch analysis Filter tool-filters sp eech signal at cutoff frequencies specified by the user Comparison tool-compares two wavefor ms spectral distance using several measures Sp eech degradation Platform: |
Size: 413153 |
Author:威威 |
Hits:
Description: 一个什么都能做的语音处理软件，Manual segmentation of speech waveforms - creates label files which can be used to train speech recognition systems
Waveform editing - cutting, copying or pasting speech segments
Formant analysis - displays formant tracks of F1, F2 and F3
Pitch analysis
Filter tool - filters speech signal at cutoff frequencies specified by the user
Comparison tool - compares two waveforms using several spectral distance measures
Speech degradation -can do what a voice processing software, Manual segmentation of speech waveforms- crea tes label files which can be used to train speech recognition systems Waveform editing- cuttin g, copying or pasting speech segments Formant ana P <0.05-displays formant tracks of F1, F2 and F3 Pitch analysis Filter tool-filters sp eech signal at cutoff frequencies specified by the user Comparison tool-compares two wavefor ms spectral distance using several measures Sp eech degradation Platform: |
Size: 412672 |
Author:威威 |
Hits:
Description: 波形和频谱双显示
记录讲话直接进入MATLAB
手动分割讲话波形-创建标签文件
波形编辑-切割，复制或粘贴
共振峰分析-显示共振轨道的F1 ， F2和F3
基音分析
过滤工具-语音信号滤波器截止频率
比较工具-比较两个波形的频谱距离使用几种措施
增加噪声-Dual time-waveform and spectrogram displays
Records speech directly into MATLAB NEW
Displays time-aligned phonetic transcriptions [e.g., TIMIT s .phn files]- see example Figure above
Manual segmentation of speech waveforms- creates label files which can be used to train speech recognition systems
Waveform editing- cutting, copying or pasting speech segments
Formant analysis- displays formant tracks of F1, F2 and F3
Pitch analysis
Filter tool- filters speech signal at cutoff frequencies specified by the user
Comparison tool- compares two waveforms using several spectral distance measures
Speech degradation- adds noise to the speech signal at an SNR specified by the us Platform: |
Size: 1180672 |
Author:wsw |
Hits:
Description: 本程序用于测量增强语音与纯净语音的对数谱距离，用于语音增强。对数谱距离越小，表明增强语音与纯净语音越接近，增强语音质量越好；反之，则增强语音质量越差。-Calculates the average log-spectral distance between CLEAN and NOISY
signals. Frames are 25ms long with 60 percent (15ms) overlap, hamming
windowed. RS is the remove silence option (default: 0) if 1, the program
uses a Voice Activity Detector to find non-speech frames and eliminates
them from calculation of LSD. FS is the sampling frequency (Default
10KHz). Platform: |
Size: 3072 |
Author:阿铁 |
Hits:
Description: COLEA is a Matlab Speech Processing Toolkit with a graphical user interface.
This program can be used to edit speech waveforms (cut, copy or paste selected speech segments) and compute spectrogramss. It includes several speech related tools including a filter tool for speech filtering, and a comparison tool for comparing two waveforms using a variety of spectral distance measures.COLEA can be used to display time-aligned phonetic transcriptions (e.g., TIMIT s .phn files) and for manual segmentation of speech waveforms. It can also perform formant analysis and pitch analysis. A manual describing COLEA is included. For more information about this program visit the web site:
http://www.utdallas.edu/~loizou/speech Platform: |
Size: 356352 |
Author:Gurkan Acı r |
Hits:
Description: 基于奇异值分解的人脸识别方法
梁毅雄 龚卫国 潘英俊 李伟红 刘嘉敏 张红梅
提出了一种将傅里叶变换和奇异值分解相结合的人脸自动识别方法.首先对人脸图像进行傅里叶变换,得到其具有位移不变特性的振幅谱表征.其次,从所有训练图像样本的振幅谱表征中给定标准脸并对其进行奇异值分解,求出标准特征矩阵,再将人脸的振幅谱表征投影到标准特征矩阵后得到的投影系数作为该人脸的模式特征.然后,对经典的最近邻分类器算法进行了改进,并采用模式特征之间的欧式距离作为相似性度量,从而完成对未知人脸的识别.采用ORL (Olivetti Research Laboratory)人脸库对本文提出的人脸识别方法进行验证,获得了100.00 的识别率.实验结果表明,本方法优于现有的基于奇异值分解的人脸识别方法,且对表情、姿态变换等具有一定的鲁棒性.
-Face recognition based on singular value decomposition method
Deliberate simultaneously Gong Weiguo Li Wei Hung Stephen Lau, Hong-Mei Zhang Ying-Jun Pan
Paper, a Fourier transform and singular value decomposition of the combination of automatic face recognition. First of all, the face image by Fourier transformation, it has the same characteristics of the displacement amplitude spectra. Secondly, all training The amplitude spectrum of the sample images given in standard face representation and its singular value decomposition, find the standard characteristic matrix, then the amplitude of spectral characterization of human faces projected onto the standard characteristic matrix of projection coefficients obtained as the face of the model features . Then, the classical nearest neighbor classifier is improved, and the use of Euclidean distance between pattern features as the similarity measure, thus completing the identification of unknown human faces. using ORL (Olivetti Research La Platform: |
Size: 58368 |
Author:houhj |
Hits:
Description: 计算源信号和噪音之间的频谱差，用于噪音估计等。-Calculates the average log-spectral distance between CLEAN and NOISY signals Platform: |
Size: 3072 |
Author:philip |
Hits:
Description: SpectralClustering performs one of three spectral clustering algorithms (Unnormalized, Shi & Malik, Jordan & Weiss) on a given adjacency matrix. SimGraph creates such a matrix out of a given set of data and a given distance function.
The code has been optimized (within Matlab) to be both fast and memory efficient. Please look into the files and the Readme.txt for further information. Platform: |
Size: 9216 |
Author:Keerthana |
Hits:
Description: 本程序用于测量增强语音与纯净语音的对数谱距离，用于语音增强。对数谱距离越小小，表明增强语音与纯净语音越接近，增强语音质量越好；反之，则增强语音质量越差。
-The procedure used to measure to enhance the voice and the pure voice of the logarithmic spectral distance for speech enhancement. More small log spectral distance, the closer that enhanced speech and clean speech, enhanced voice quality, the better the contrary, the enhanced voice quality of the worse. Platform: |
Size: 3072 |
Author:分界线 |
Hits:
Description: 车辆监测用测速雷达是依据多普勒效应原理实现的。由雷达发出一束微波，遇被测目标（车辆）时微波被反射回来，再由雷达接收反射波。如果目标相对于雷达有距离上的运动，反射波的频率将与发射频率发生差异，而这种差异的大小正比于目标与雷达的相对运动速度。于是，雷达通过检测反射波频率和发射波频率的差，就可以计算出被测车辆的移动速度。本次课程设计是利用离散付里叶变换进行频谱分析，设计数字滤波器组，并对滤波器组加窗降低副瓣，通过频域方法测量速度。-Vehicle monitoring using radar gun is based on the realization of the principle of the Doppler effect. By the radar emits a microwave, in case the measured target (vehicle) when the microwave is reflected back, and then by receiving the reflected radar waves. If the target relative to the radar on a distance of motion, the frequency of the reflected wave and the emission frequency of the difference, and this difference is proportional to the relative target and radar velocity. Thus, by detecting the reflected radar wave frequency and the frequency difference between the transmitted wave, we can calculate the movement speed of the vehicle under test. This course is designed to take advantage of the discrete Fourier transform spectral analysis, digital filter design group, and filter bank windowed lower sidelobes by frequency domain methods to measure speed. Platform: |
Size: 489472 |
Author:陈权 |
Hits:
Description: Environmental remote sensing is the measurement, from a distance, of the spectral features of the Earth’s surface and atmosphere. These measurements are normally made by instruments carried by satellites or aircraft, and are used
to infer the nature and characteristics of the land or sea surface, or of the atmosphere, at the time of observation. Platform: |
Size: 22390784 |
Author:roshan |
Hits:
Description: 给定离散地震动加速度数据a、反应谱控制周期点tp、离散时间间隔dt、阻尼比z，计算地震动加速度反应谱rspa以及最大反应值出现的时刻tMax。-Given the discrete ground-motion acceleration data a, the response spectral controlling period tp, the discrete time distance dt, and the damping ratio z, calculate the ground-motion acceleration response spectrum rspa and the time loction of the occurrence of maximum response. Platform: |
Size: 1024 |
Author:Zhang YS |
Hits:
Description: 语音增强之前先进行端点检测，对有话帧和噪声帧作不同处理，利用对数频谱距离进行端点检测。-Speech enhancement for endpoint detection, before to have words for different frame and noise frame processing, using logarithmic spectrum distance for endpoint detection. Platform: |
Size: 1024 |
Author:黄燕 |
Hits:
Description: 进一步采用基于距离和曲线形态的双尺度相似性度量谱聚类算法进行聚类处理，通过求n 个二次规划问题，就可以求得相似度矩阵W，降低了谱聚类算法对参数的敏感性，使算法更稳定(Furthermore, we use the two-scale similarity measure spectrum clustering algorithm based on distance and curve shape to carry out clustering. By finding n quadratic programming problems, we can obtain the similarity matrix W and reduce the sensitivity of the spectral clustering algorithm to the parameters Sex, make the algorithm more stable) Platform: |
Size: 2048 |
Author:去海边看海豚
|
Hits:
Search - spectral distance