资源列表
dtdp
- 深刻理解加窗思想在语音语音信号处理的作用，掌握矩形窗、汉宁窗、哈明窗的算法。理解窗长和窗移对计算语音信号的短时过零率、短时能量、短时平均能量的影响，掌握设定合适的短时过零率阈值、短时平均能量阈值来实现语音信号端点的检测。-an implementation of double-threshold method for audio endpoint detection algorithm
wra
- 在上一次实验的基础上，进一步理解加窗思想在语音语音信号处理的作用和语音信号时域处理的基本方法，掌握基于短时自相关函数的基音周期估计的算法，理解窗长与基因周期之间的关系。完成语音基因计算。-an implementation of the pitch estimation algorithm based on short-time autocorrelation function
MiCode-SoundRecorder-15aa813
- 一个仿磁带录音程序，喜欢的朋友下载看看！-An imitation of the tape recording procedures
SpeechToken
- 调用语音库来朗读文本例子，支持中文及英语朗读-Call the voice library to read aloud the text examples to support Chinese and English reading
DrvLib
- 文件为语音合成以及识别 多媒体开发的驱动库源代码 仅供参考-The drive library source code files for speech synthesis and recognition multimedia development for reference only
telephone
- 双音多频电话拨号系统,模拟电话拨号，拨号确认后自动弹出已拨号码-Dual-tone multi-frequency telephone dialing system
codes
- matlab code for digit recognition
syll
- syllable recognition in continuous speech
corr
- provides a correlation coefficients for two spoken words
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
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,
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.