搜索资源列表
Speech Recognition
- Introduction Applications Comparing Automatic Speech Recognition(ASR) versus image processing About ASR Types of ASR and differences ASR by Hidden Markova Models Overall recognition system Isolated word recognition
11
- 源程序输入串的预处理，为单词识别做好准备-Preprocessing source code input strings, prepare for word recognition
1003
- 这个关于语音识别的文章，介绍了HMM模型的参数优化的 问题，以及HMM模型的孤立字识别中的应用。-This article on speech recognition, introduced the HMM model parameter optimization, as well as isolated word HMM model to identify the application.
melodyRecognition
- 自动语音识别源码对非特定人的孤立词语音识别算法 进行研究。考虑到语音识别技术在嵌入式系统处理能力较弱、存储空间有限的问 题上进行算法的选择和优化，以提高系统的鲁棒性，减少系统的 -Automatic speech recognition source code for non-specific human isolated word speech recognition algorithm research. Taking into account the voice recogni
imageProcessing
- In this project we have implemented a method for recognition of Printed Characters by extracting some features from the gray scale image using a Bank of Gabor Filters. In this project we initially segment the given word image into words and words in
paper2
- 语音识别技术主要包括特征提取技术、模式匹配准则及模型训练技术三个方面。此外，还涉及到语音识别单元的选取。选择识别单元是语音识别研究的第一步。语音识别单元有单词（句）、音节和音素三种，具体选择哪一种，由具体的研究任务决定。-Speech recognition technology, including feature extraction techniques, pattern-matching criteria and the three aspects of model training t
Mel_RBF
- 基于Mel倒谱特征和RBF网络的孤立词语音识别方法-Mel-based cepstral features and RBF networks isolated word speech recognition method
Cforspeech
- ：用C 语言实现了一个用于控制家电开关的声音模块. 该声音模块采用当前语音识别系统的主流技 术——隐马尔可夫模型（HMM）技术，以及线性预测倒谱计算和矢量量化技术. 命令（单词）的正确识别率 在97 以上. 介绍了声音模块的设计方案，并就实现该声音模块的过程中所遇到的具体问题进行了讨论.-: The C language realization of a switch used to control the voice module appliances. The sound modul
Project2-2
- training and then recognition of a spesified word in MATLAB
DTWspeech
- 本 文 首先 介绍了语音识别的研究和发展状况，然后循着语音识别系统的 处理过程，介绍了语音识别的各个步骤，并对每个步骤可用的几种方法在实 验基础上进行了分析对比。研究了语音信号的预处理和特征参数提取，包括 语音信号的数字化、分帧加窗、预加重滤波、端点检测及时域特征向量和变 换域特征向量.其中端点检测采用双门限法.通过实验比对特征参数的选取， 采用12阶线性预测倒谱系数作为识别参数。详细分析了特定人孤立词识别算 法，选定动态时间弯折为识别算法，并重点介绍其设计实现。 在
DGP_005
- 日文汉字的单字识别，涉及到对图像的二值化，骨架提取，模式匹配，识别率比较高-Kanji word recognition, relates to the binary image, skeleton extraction, pattern matching, a relatively high recognition rate
speechRecognition
- isolated word for speech recognition lecture notes
WordRecognition_final
- Developing an Isolated Word Recognition System in MATLAB
word
- 编译原理作业，一个C++的单词识别。可以识别C++大部分单词-Compiler theory work, a C++, word recognition. Can identify most of the word C++
WordMatch
- 实现单词的自动匹配识别，如果不成功会返回失败标志-Automatically matched to achieve word recognition, if unsuccessful will return failure signs
RecognitionofOffLineHandwrittenArabicWordsUsingHi
- Hidden Markov Models (HMM) have been used with some success in recognizing printed Arabic words. In this paper, a complete scheme for totally unconstrained Arabic handwritten word recognition based on a Model discriminant HMM is presented. A
Carlicenseplaterecognition
- 基于Matlab的车牌识别程序，是我自己做的，不是特别好，但基本框架已做好，还有word报告。-Matlab-based license plate recognition program, is my own, not particularly good, but the basic framework has been doing a good job, there is word report.
DTW
- DTW（Dynamic Time Warping，动态时间归整）算法，该算法基于动态规划（DP）的思想，解决了发音长短不一的模板匹配问题，是语音识别中出现较早、较为经典的一种算法。用于孤立词识别，DTW算法与HMM算法在训练阶段需要提供大量的语音数据，通过反复计算才能得到模型参数，而DTW算法的训练中几乎不需要额外的计算。所以在孤立词语音识别中，DTW算法仍然得到广泛的应用。 -DTW (Dynamic Time Warping, dynamic time warping) algorithm
simple-isolated-word-recognition
- 可以实现简单孤立词的识别和训练，内有1到9的录音，可以自己训练。-Can achieve a simple isolated word recognition and training, there are 1 to 9 of the recording, you can own training.
Character-recognition
- 自己制作基于“欧氏距离的算法”来识别文字的相似性，从而来识别手写文字的程序，开发环境是matlab.需要讲手写的字加到字库才可以哦。-Produce their own based on the " Euclidean distance algorithm" to identify the similarity of the text, handwritten text in order to identify the procedures, the development e