资源列表
julius-4.3.1.tar
- Julius 是一种高性能，两通大词汇量连续语音识别（LVCSR）语音相关的研究和开发的解码器软件。基于字的N-gram和上下文相关的HMM模型，它可以进行几乎实时实时解码目前大多数电脑在60K字听写任务。完全纳入，如树的N-gram词汇，保，跨词的上下文依赖处理，包围梁搜索，高斯修剪，高斯的选择，除了搜索效率等各大搜索技术，它也是模块化小心从模型结构独立，如共享状态triphones的和并列混合模型与任意数量的混合物，州或手机，支持各种HMM的类型。采用标准格式，以配合HTK的，债务工具中央结
qpsk
- code division multiple acce-code division multiple access
yinyue
- 本代码写是关于音乐的代码，现在上传的只是其中的一部分-This code is written about music code, only part of which is now uploaded
dsp
- fir录波器，可以合成不同的滤波波形，里面含有详细的教程，对初学者很有用哟-fir wave recording, you can synthesize different filtered waveform, which contains a detailed tutorial, very useful for beginners yo
jiance
- 用于对语音信号的共振峰进行检测，从而进行语音识别或语音合成。-For formant speech signal is detected, thereby performing a voice recognition or voice synthesis.
DTW
- 该文件为基于DTW的孤立词识别系统（特定人、小词汇量，未采用鲁棒语音识别技术）-The document DTW for isolated word recognition system based on (a specific person, small vocabulary, did not use robust speech recognition technology)
HMM
- 该文件为基于HMM的孤立词/连接词识别系统-The document is based on isolated word HMM' s/conjunctions recognition system
sphinxRec
- 自己搭建了一个pocketsphinx sphinxbase的win下的语音识别程序，用vs2010打开 pocketsphinx.sln 编译pocketsphinx_continuous 项目，调试输入命令好都写好了，直接对着mic喊话，然后看识别cmd下的识别结果 -This speech recognition program is build with pocketsphinx and sphinxbase under the Win7 OS, Open the pockets
dynamic_time_warping_v2.0
- Copyright (C) 2013 Quan Wang <wangq10@rpi.edu>, * Signal Analysis and Machine Perception Laboratory, * Department of Electrical, Computer, and Systems Engineering, * Rensselaer Polytechnic Institute, Troy, NY 12180, USA */ /**
voicebox
- VOICEBOX is a speech processing toolbox consists of MATLAB routines that are maintained by and mostly written by Mike Brookes, Department of Electrical & Electronic Engineering, Imperial College, Exhibition Road, London SW7 2BT, UK. Several of the ro
mp3_toolbox_v2.0
- ncludes 2 functions to write and read MP3 files. It works like the commands WAVWRITE and WAVREAD. 1.- Just unpack in the toolbox folder under the MATLAB directory. 2.- Set the MATLAB search path to include that folder. This version was m
pitch
- 基音检测，通过计算最大值，检测其位置，再检测零值的位置来实现.-Pitch detection, by calculating the maximum and its position, and detect the position of zero.