资源列表
Speaker_identification
- Speaker identification security improvement by means of speech watermarking 语音别识SCI文献-Speaker identification security improvement by means of speech watermarking
voice
- 汉语连续语音识别中上下文相关的声韵母建模.pdf-Chinese continuous speech recognition context-sensitive acoustic modeling finals. Pdf
yuyinxinhaochuli
- 语音信号处理中的所有基本的算法的代码（C语言版）-Speech signal processing algorithms in all the basic code (C language version)
recognition.RAR
- 语音识别基本原理的英文原版 需要NLC电子图书格式阅读器打开-Basic principles of speech recognition requires NLC original English format reader to open e-book
zdyyxt
- 自动语音系统,用于板卡或电信交换机的通话录音与语音检测。次包包括ivr应用系统和二次开发函数接口和实例 -automitic speech
speechrecdemo
- c++speech ，还不错的.我就是从这个程序开始学习SPEECH SDK的。-c++speech
ztnorm
- 对于说话人语音识别得到的分数，先进行2次znorm规整，再做一次tnorm的规整化，使得分数更加合理。-Speaker voice recognition score, the first 2 times znorm structured, do it again regularization tnorm, more reasonable scores.
tnorm
- Tnorm利用大量冒充者模型来得到均值u和方差δ，再用这两个数据带入到score =(score-u)/δ得到规整化之后的分数。这样使得结果更加合理。-Tnorm impostor model to get mean u and variance δ, then these two data into the score ' = (score-u)/δ score after regularization. This makes the results more reasonable.
equinox-srepm_V1
- 计算说话人识别系统的全局EER和DCF，以及平均的EER，DCF-Calculation of the overall situation of the speaker recognition system EER and DCF, and average EER, DCF,
score_tradeoff
- 计算说话人识别系统的全局EER，DCF和平均EER，DCF-Calculation of the overall situation of the speaker recognition system the EER, DCF and average EER, DCF
znorm
- 通过一些额外的语音对训练好的说话人模型进行测试统计出其输出评分的均值和方差（u,δ）当真正进行测试时，对输出模型的分数score，用规整之后的score =（score-u）/δ代替。使得结果更加合理。-Speaker model trained by some additional voice test statistics of the mean and variance of its output rated (u, δ) when the real test, the fraction
corr
- provides a correlation coefficients for two spoken words