搜索资源列表
情感识别
- 压缩包中的一系列matlab程序实现了“特定人群语音情感识别”这一新颖的研究课题。具体介绍请见压缩包中的论文。-compressed in a series of Matlab program of "specific emotional crowd voice recognition" of the new study. Specific details of compressed see the papers.
hmm.zip
- 隐马尔可夫链模型和例程（包括前向、后向算法、Viterbi解码以及为了减少概率数值计算误差编写的对数运算程序）,Introduction to Hiden Markov Model and Example Codes
HVite.rar
- 实现HMM算法，VQ算法，以及神经网络算法的语音识别程序,Realize the arigthom of HMM(training),VQ and NN for speech recognition
bp-matlab
- bp神经网络的程序代码，可以应用于语音识别，图像识别等 -bp neural network code, can be applied to speech recognition, image recognition, etc.
Whisper
- 语音识别程序，为毕业设计实验程序。 -A voice recognition program, graduate design
Contains-examples-HMM
- matlab程序，基于隐马尔科夫的语音识别源程序，内含例子，以及详细说明各个子程序的作用。-Contains examples, and detailed descr iption of the role of each subroutine. Speech recognition based on hidden Markov source,
xysb2012
- 本程序能改实现语音识别，是基于神经网络的语音识别-Program to achieve the BP neural network-based speech recognition, contains the original data
Intelligent-Robot
- 语音识别+机器人+超声波测距综合应用方案 采用特定人识别技术，程序开始时用户需要对语音识别进行训练，每条指令训练两次，训练成功后，才开始真正的语音辨识，针对用户发出的不同语音指令，机器人执行不同的动作，在动作过程中进行超声波测距，遇到障碍物停止动作，并发射飞盘-Specific recognition technology for speech recognition the+ robot+ ultrasonic distance measurement applications, the
MFCC
- MFCC参数提取的所有程序，已接近人耳听觉的特点在语音识别领域得到广泛应用-MFCC parameter getting
BP
- 自己写的BP神经网络程序，可用于语音识别-Write your own BP neural network program, can be used for voice recognition
Speech-Recognition
- 用matlab编的基于DTW和MFC算法的语音识别程序，识别效果还不错-Use matlab compiled based MFC algorithm DTW and speech recognition program to identify the results were good
ac275
- 一个计算声子晶体结构的一维传递矩阵法,完整的基于HMM的语音识别系统，汽车课设货车Matlab驱动力图程序。- A one-dimensional transfer matrix method to calculate the phonon crystal structure, Complete HMM-based speech recognition system, Car class-based truck driver trying to Matlab program.
DeepLearning
- 包含神经网络、卷积神经网络、深度信念网络等深度学习程序，该程序可以用于语音识别、分类等处。(Deep learning programs including neural network, convolutional neural network and deep belief network can be used for speech recognition, classification and so on.)
spkID
- 利用mFCC特征提取算法进行语音信号的特征提取，然后利用ＧＭＭ识别出特征人，计算目标得分，程序效果ＯＫ。(The extraction algorithm for feature extraction of speech signal using mFCC features, and then use GMM to identify a specific target, calculate the score, the effect of OK program.)
CNN+CTC语音识别算法
- 这个程序是用的一个深度卷积神经网络来做的，整个程序分为两部分，声学模型和语言模型，效果还是可以的。