搜索资源列表
HTKApplication(1)
- HTK搭建语音识别系统(一)讲义，中文，详细讲解各步骤以及所用HTK函数，文档-HTK to build speech recognition system (1), Chinese
test
- MySQL数据库 其他数据库 汇编语言 SCSI/ASPI 编译器/解释器 磁盘工具 语音合成与识别 编辑器/阅读器 杀毒 中文信息处理 FlashMX源码 并行计算 书籍源码 Delphi控件源码 操作系统开发 中间件编程 MacOS编程 + 电子书籍 VC书籍 Java书籍 Delphi/CppBuilder
nannvshengshibie
- 本文通过对男性和女性声音的语音特征的研究，发现男女声的基音频率存在较大的差异，并设计了基于基音频率分析的男女声识别系统。男女声识别系统由以下三个模块电路构成：话筒放大器，低通滤波器，半波整流电路，单片机测量控制模块。话筒放大器采用NE5532P音前置芯片，对语音信号进行放大；八阶低通滤波器MAX293完成基音信号的提取；单片机STC12C5410AD实现频率测量和控制输出功能。经仿真与电路实测，男女声的识别效果良好。-In this paper, the voices of male and f
BiJi
- 自己整理的语音识别相关理论笔记 是囊括了目前的语音识别的基础理论，对于语音方面编程的朋友可以作为资料参考-Finishing his speech-recognition related theory notes that the current speech recognition include the basic theory for the voice of a friend in programming can be used as reference material and
HMM
- HMM隐马尔科夫模型的学习资料，有实例介绍-HMM Hidden Markov Model of learning materials
htk
- HTK是一个用以建立和使用马尔可夫模型的工具包。HTK主要被用于语音识别，但它也被广泛的应用于其它很多领域，像语音合成、特征识别、DNA序列研究。-HTK is a Markov model for the establishment and use of the toolkit. HTK is primarily used for voice recognition, but it is also widely used in many other areas, such as speech
aboutphonelinearnovels
- 这是我收集来的有关语音信号非线性处理方面的小论文，主要有关语音非线性分析、研究、预测编码以及识别方面，希望对大家有帮助！-This is what I gathered the voice signal processing, nonlinear small papers, mainly the voice of nonlinear analysis, research, and to identify aspects of predictive coding, we want to help!
语音识别关键性技术的MATLAB仿真实现
- 语音识别关键性技术的MATLAB仿真实现.pdf-Voice recognition key technologies MATLAB simulation. Pdf
HMM
- HMM识别孤立词的研究与实现,有助于学习语音识别-HMM isolated word recognition and implementation of research, contribute to learning speech recognition
yuyingshibie
- 基于SOPC的语音识别系统 语音分帧、加窗及端点检测部分程序细节-The speech recognition system based on SOPC Speech frame, window and endpoint detection part program details
456
- 基于语音信号与心电信号的多模态情感识别研究和处理-Based on speech signal with the ecg signal modal emotion recognition research and treatment
vq
- 基于vq的语音识别代码，很好用，请大家认真看，受益匪浅。-Speech recognition based on vq code, useful, please read and benefit a lot.
voice
- 主要是进行语音识别，录入几个人的语音，保存音频后，最后进行语音匹配，识别出来。-Mainly for speech recognition, speech input a few people, save audio, voice last match identified.