资源列表
Audio-Features
- MATLAB Programs to calculate various audio features
JLDATA
- 摘 要：本论文主要研究了语音识别的基本原理,对语音识别系统的构成进行分析处理,其中包括预处理、特征参数提取、建立模块库、识别匹配几大部分。预处理又包括语音采样、预加重、加窗（汉明窗）、端点检测；特征提取的参数是梅尔频率倒谱系数MFCC。 该语音系统采用的是动态时间伸缩算法(DTW)，研究对象是特定人的语音识别，并在MATLAB平台上实现。为了进行后续研究，首先使用电脑中的录音系统录制了阿拉伯数字0—9的语音文件，并转化成 “.wav”格式的文件。-Abstract: This thesis
hde code
- hde code for speech recognification using the HMM and GMM
frft
- 基于统计特征的语种识别算法分析与实现。1.提取语音的客观统计特征；2、通过分类器建立训练学习模型；3、将模型运用于汉语、英语、日语等语种识别实验，与人的主观感觉做对比-Based on statistical language identification algorithm analysis and Realization of objective statistics. The extraction of speech features 2, the classifier built th
moban
- matlab基于DTW的非特定人语音识别，单模版匹配与最近邻- matlab independent speech recognition, DTW-based single-mode version matching and nearest neighbor
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
Voice
- 三种降噪，回声和变调的语音信号处理，含UI界面-Three kinds of noise reduction, echo and tone of voice signal processing, including UI interface
Speech-synthesis-.
- 基于线性预测系数和预测误差和基因参数的语音合成实验，学校实验。-Based on linear prediction coefficient and prediction error and genetic parameters of speech synthesis experiment, school experiment.
pinputu
- 均匀噪声、高斯噪声、粉红噪声的频谱图、对数谱、功率谱-Uniform noise spectrum Gaussian noise, pink noise, logarithmic spectrum, power spectrum
Synthesizer-master
- speech synthesis system, text to speech system to speech for user loud and good quality for you.
DTW-isolated-word-speech-recognition
- 基于动态时间规整的孤立词语音识别，用梅尔倒谱系数作为识别特征。-Based on dynamic time warping of isolated word speech recognition, using Mel s coefficient as the recognition feature.
Untitled
- 语音信号处理，增强技术，基本谱减法进行语音增强的matlab程序-Speech signal processing, enhancement techniques, basic spectral subtraction speech enhancement matlab program