资源列表
93562307GMM-EM
- GMM-EX gmm语音转换模型，以及里面详细的ex聚类程序介绍-GMM-EX GMM voice switching model, and the EX clustering, there are detailed introduced program
final-vioce
- 语音识别 dtw算法 mfcc特征提取 用于特定人识别-Speech recognition dtw mfcc
PersonalRecord
- 非常实用的java小实例，个人录音，实现了很简单的小功能，对于我们初学者很有帮助哦，拿来分享给大家。-Very practical examples of java small, personal recording, to achieve a very simple little feature, very helpful for us beginners Oh, bring to others.
61_Record
- 全自动语音商品介绍机，能自动介绍产品的信息，且能自动触发-langue intruder
SPEAKN
- 输入文本后将其转换成语音,是一个简单的文语转换实例-Text to Speech
LPC-Linear-Predictive-Coding
- 语音识别中主流的共振峰提取方式LPC核心源码和说明文件-Speech recognition in the mainstream way of LPC formant extraction core source code and documentation
chengxu
- 基于动态时间规整的语音识别系统研究及其实现，用C语言编程完成-Dynamic time warping-based speech recognition system and its implementation, complete with C language programming
WindowsApplication
- c# 朗读文本支持中文发音，可做文本朗读器使用-c# read text support Chinese pronunciation, do text to speech uses
julius4-segmentation-kit-v1.0.tar
- 日本Julius强大的音素分割程序,用于语音识别领域-Japanese Julius powerful phone segmentation toolbox for speech recognition
soundcollection
- 对语音进行采集，可以播放录入的声音，对语音处理学习方面有帮助！-It can collect sound,and play it. It is helpful for learning speech technical.
PLAY
- 把语音芯片ISD1420录放音时间20秒分成20段，每段一秒，调用录音子程序，录入语音，建立语音库，语音录入结束后，根据段地址，调用放音子程序，还原原来录入语音信号。- The voice chip ISD1420 sound recording time of 20 seconds is divided into 20 segments, each second, a subroutine call recording, voice input, speech database estab
time_extend
- 语音延长、变速处理程序，实现语音信号时域延长； 主要步骤是先对原始语音信号进行加窗，再对加窗后的语音信号进行时域扩展； 以上处理之后语音信号可能会带进新的噪声，所以再对处理后的语音信号，使用FIR滤波器进行去噪处理。-Voice extending process, extending the time-domain voice signal The first major step is added to the original speech signal window, a