語者辨識系統根據應用領域的不同可以區分為語者識別(Speaker Identification)及語者確認(Speaker Verification)兩個類別。本論文設計一個卷積神經網路(Convolution Neural Network)架構用於語者識別，透過卷積神經網路區分不同語者之間的語音特徵，並且將比較在不同的初始學習速率、權重初始化方法以及特徵擷取方法下，語者識別模型效果之差異。對於語者確認模型則會利用孿生神經網路(Siamese Neural Network)來實現，透過計算基準語者與測試語者在特徵空間中的距離，進而判斷兩位語者是否相似。最後，會把語者識別與語者確認模型介面化，讓使用者能方便使用。;The speaker recognition system can be divided into two categories: “Speaker Identification” and “Speaker Verification”. This thesis designs a convolutional neural network architecture for speaker identification in order to distinguishing the speech features between different speakers, and compare the effect of the speaker identification model under different initial learning rates, weight initialization methods, and feature extraction methods. As for the speaker verification model, it’s implemented by using the siamese neural network. The siamese neural network determines whether the two speakers are similar by calculating the distance between the base speaker and the input speaker in the discriminative feature space. Finally, we design a graphical user interface for user to use.
