搜索资源列表
Statistical-language-model
- 汉语语音识别中统计语言模型的构建及其应用, 清华大学硕士论文, 2-Chinese Speech Recognition statistical language model and its application, Tsinghua University, master s thesis, 2000
1
- 一个基于遗传算法与mp的外文文献,讲的很清楚明了,有参考价值-VOICED/UNVOICED SPEECH DISCRIMINATION IN NOISE USING GABORATOMIC DECOMPOSITION
Signal-Processing-Software
- A Speech Tool Software for Signal Processing Applications
PCA
- 针对稀疏表示识别方法需要大量样本训练过完备字典且特征冗余度较高的问题,提出了结合过完备字典学习与PCA降维的小样本语音情感识别算法.该方法首先用PCA降维方法将特征降维,再将处理后的特征用于过完备字典训练与稀疏表示识别方法,从而给出了语音情感特征的稀疏表示方法,并确定了新算法的具体步骤.为验证其有效性,在同等特征维数下,将方法与BP, SVM进行比较,并对比、分析语音情感特征稀疏化前后对语音情感识别率、时间效率以及空间效率的影响.试验结果表明,所提出方法的识别率比SVM与BP高 与采用稀疏化前的
emospeech
- speech emotion detection
s16p06
- power quality monitoring has advanced to an important tool for system evaluation.the increased amount of recorded data requires more sophisticated analysis methods. the paper describes the development and operation of a system for automated classific
Disordered-Voice-Database-flyer-2007-opt-(1)
- KayPENTAX has recorded to CD-ROM a database developed by the Massachusetts Eye and Ear Infirmary (MEEI) Voice and Speech Lab.
htkbook.pdf
- HTK Book是非常好的入门书,这本书实际上是剑桥大学发布的著名开源工具包HTK Speech Recognition Toolkit 的说明书,近400页,厚厚的一本。如果有时间、有兴趣,可以照着书中的第二章在电脑上做一遍,你将搭建出一个简单但基本完整的语音识别系统,能识别简单的英语数字串。-htk book
HTS-Introduction
- An Introduction to HMM-Based (hidden Markov model) Speech Synthesis
chengxu
- 这里是关于语音增强算法研究的程序,有需要的朋友可以下载参考-Here is the speech enhancement algorithm on the procedure, a friend in need can be downloaded reference
VAD_MFCC
- Voice Activity Detection. Fundamentals and Speech Recognition System Robustne-Voice Activity Detection. Fundamentals and Speech Recognition System Robustness
testpnn
- 对于语音识别功能实现的一个算法,有一定的参考价值。-For a speech recognition algorithm to achieve, there is a certain reference value.
viterbi
- 语音识别HMM算法中的解码功能的程序,其中是根据观测序列和已知模型去求状态序列-Speech recognition HMM algorithm decoding process, which is to seek observer status in accordance with the sequence and the known sequence of the model
mfcc
- 在语音辨识(Speech Recognition)和语者辨识(Speaker Recognition)方面,最常用到的语音特征就是「梅尔倒频谱系数」(Mel-scale Frequency Cepstral Coefficients,简称MFCC),此参数考虑到人耳对不同频率的感受程度,因此特别适合用在语音辨识。
htkbook_CH_EN
- 隐马尔可夫模型工具包(HTK)是一种便携式工具包构建和操纵隐马尔可夫模型。 HTK主要用于语音识别的研究,虽然它已被用于许多其它应用,包括研究,语音合成,字符识别和DNA测序。 HTK是使用在世界各地的数百个网站。 该文档主要包含htkbook的中英文版本,方便HTK初学者使用和学习。-The Hidden Markov Model Toolkit (HTK) is a portable toolkit for building and manipulating hidden Markov
ann_ppt
- 清华大学人工神经网络ppt讲稿 内容不错-Tsinghua artificial neural network ppt good speech content
yuanma
- 基于matlab的语音合成以及移动基频实现变声调-speech synthesis
encode
- Matlab for speech coding encode
yuyinxinhaochuli
- 关于语音信号处理的书,详细介绍了语音信号处理中的各种知识,开发过程等-Books on speech signal processing, speech signal processing described in detail in a variety of knowledge, the development process, etc.
Bluetooth_Full_Duplex
- Simulink® and Stateflow® model of a full duplex Bluetooth communication link transmitting HV1, HV2, HV3, and SCORT [1] voice packets, and DM1 data packets. A system parameters block configures the whole model s packet type, slot pair and chan