The structure of PMN is a four layer feedforward neural networks(FNN), where the Gaussian probability density function is realized as an internal node.
英
美
- PMN網(wǎng)為一個(gè)四層前饋網(wǎng),它構成一個(gè)貝葉斯分類(lèi)器,實(shí)現多類(lèi)分類(lèi)的貝葉斯判別,把輸入的說(shuō)話(huà)人語(yǔ)音數據模型參數通過(guò)網(wǎng)絡(luò )變換為輸出的說(shuō)話(huà)人判定。