资源列表
aquila-master
- mfcc特征提取， dtw匹配，老外写的，值得学习。- feature extraction, including MFCC and HFCC features, widely used in speech recognition * a simple DTW (dynamic time warping) pattern matching algorithm which also can be used for recognition
ZY1420_Clock
- 这是ZLG写的ZY1420A分段录音播放应用设计以及语音报时时钟的设计原理。里面有ASM程序-It is written in ZY1420A ZLG application design and sub-audio player design principle of speaking clock. ASM program inside
Speech-recognition-speech-sdk-5.1
- 语音识别 使用微软语音识别库speech sdk 5.1-Speech recognition speech sdk 5.1
voice-spectrum
- 语音的短时能量、过零率分析 语音的能量E和过零率Z是两个比较重要的时域参数，通过总结这两个参数在语音段和静音段的特点，可以检测出语音的边界，可以总结出这两个参数分别在声母、韵母及静音部分的特点。 -The voice of the short-term energy, zero crossing rate analysis of the voice of the energy E and the zero crossing rate Z are two of the more im
CRGAB
- C语言开发工具包 （包括制表键宽度的变化，图形图像的处理，字符串的处理等等）-C-language development tools (including tabulation bond width changes, graphic image processing, string handling, etc.)
LMSwithUncorrelatedCaussiandata
- 本文是关于LMS算法在非相关的高斯噪声下的收敛性！希望对大家有用-paper on the LMS algorithm in the non-Gaussian noise under the Convergence! We hope to useful
lms-rational
- lms rational file , usecase diagram , class diagram -lms rational file , usecase diagram , class diagram ...
fillPcmHead
- C语言实现对PCM编码格式的wav文件，进行文件切割，分段的操作，-C language implementation of the PCM encoded wav file format for file cutting segmented operation,
A-Modified-Spectral-Subtraction--
- 关于语音去噪的iEEE论文，对进行语音信号去噪处理有很多的帮助-IEEE papers about speech denoising, the speech signal denoising processing have a lot of help
SPEECH-EMOTION
- 首先需要用户使用用户名和密码登录，然后可以实现特定人的情感识别-The first requires the user to use the username and password, and then can realize the emotion recognition of specific human
读者语音源码
- 把通过TTS引擎把文本转化为语音输出。
matlabyuyinshibieshu
- 语音识别的一个重要文件，LPCC的，大家看看，支持一个