资源列表
simon-0.4.0
- 跨平台开源语音识别软件Simon发布了v0.4版。新版历经了多年的开发，主要新特性有：全新的语音识别层；改进上下文感知准确性和性能；新的对话系统引入脚本变量、整合模板系统、数据引擎和文本语音输出，能支持与用户的完整对话；新的样本评审工具Afaras，Akonadi命令插件，-The project provides a ready-to-use interface for the julius CSR engine for a handicapped child which is not abl
pujianfayuyinzenqiang
- 利用谱减法对语音的背景噪声进行消除，matlab仿真 仿真通过，自带录制好的语音-Using spectral subtraction of background noise on speech is eliminated, through the MATLAB simulation, with recorded speech.
speech_recognition_based_on_DTW
- 基于动态时间规整,解决了发音长短不一的模板匹配问题，达到语音识别的目的-speech recognition based on DTW
Log_Spectral_Distance
- 对数谱失真测度，可以用于语音信号处理后的测试，如语音增强，语音编码，语音转换，语音识别等。-Log_Spectral_Distance，it can be used for testing speech signal.such as speech enhancement、speech encoding、speech convert and speech reconlization
SNR_estimate
- 总信噪比测试，用于对处理后的语音进行性能测试，尤其是对噪声进行处理，如带噪语音的语音增强，语音编码等。-The total SNR test, post-processing for voice performance testing, especially for noise processing, such as noisy speech for speech enhancement, speech coding.
MMSE
- 一种基于最小均方误差的噪声估计算法，实现语音增强，算法可以直接使用，已调试通过。-Based on the minimum mean square error of noise estimation algorithm, speech enhancement algorithm can be used directly, have been debug through.
low-complexity-noise-estimation
- 一种低复杂度的噪声谱跟踪算法，用于语音增强和语音识别中，文件夹内有参考文献。-A low noise spectral tracking algorithm complexity, for speech enhancement and speech recognition, there are references folder.
VOICEBOX
- Voicebox toolbox for Matlab
speaker
- linux下的说话人辨认，录音10次，识别1次，基于kmean-speaker verfication under linux，based on kmaen. It works.
kanong
- 可以用MATLAB实现卡农歌曲的播放 非常逼真 跟真的歌曲播放一样 解压缩即可-MATLAB can be used to achieve the canon of songs to play with really very realistic song plays as unzip
ACF
- 采用自相关法提取语音信号的基音周期，根据男女生基音频率的不同，识别说话人性别。-Gender recognization system based on ACF
CAMDF
- 采用CAMDF方法提取语音的基音频率，并根据男女生基音频率的范围不同，识别说话人的性别。-Gender recognization based on CAMDF