资源列表
[语音合成与识别] znorm
说明: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<吴聿修> 在 2025-06-20 上传 | 大小:2kb | 下载:0
[语音合成与识别] score_tradeoff
说明: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<吴聿修> 在 2025-06-20 上传 | 大小:2kb | 下载:0
[语音合成与识别] tnorm
说明: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.<吴聿修> 在 2025-06-20 上传 | 大小:2kb | 下载:0
[编辑器/阅读器] Reset-Item-DARKEDEN-V6.64
说明:REset sklls e tudo num sei oq<sidney> 在 2025-06-20 上传 | 大小:2kb | 下载:0
[中间件编程] new
说明:一对蓝牙模块相互通信,一块接电脑,另一块接单片机。单片机通过串口将接受 到的数据在lcd上显示出来-A Bluetooth module to communicate with each other, one connected to the computer, another a connected microcontroller. Microcontroller through the serial port to receive the data displayed on the lcd<林子> 在 2025-06-20 上传 | 大小:2kb | 下载:0