在語者辨識中，有效的訓練語料是非常重要的，因為是以其來建立語者模型，所以對辨識效果有很大的影響。傳統的語者模型都是以最大相似度為準則，雖然在大量的訓練語料下有很好的效果，但在極少量的訓練語料下卻不然，並且因為最大相似度估計的方法，是利用同一個語者的訓練語料去訓練此語者的模型，而跟其他語者的訓練語料則無相關。由於此種模型訓練時並沒有考慮到語者辨識時，語者模型互相間的關係，所以在語者辨識時容易產生混淆。因此近年來有所謂的鑑別式聲學模型訓練方式被提出來，不以最大化訓練聲學語料的相似度為目標，而以最小化分類錯誤為目標。 本論文中我們使用最小錯誤鑑別式重新去訓練語者模型，並利用支撐向量機來改善最小錯誤鑑別式，由於最小錯誤鑑別式在競爭語者數量的設定方面不夠強健，所以我們透過語者模型對調適語料的分數，附上類別標籤後來訓練支撐向量機，再由其支撐向量選取競爭語者，使選取競爭語者這方面比傳統最小錯誤鑑別式較有強健性，也有較高的語者辨識效果。 In speaker recognition, it is important to have effective training data to train speaker models which have a great effect on recognition performance. In abundant training data, traditional speaker models which is based on maximum likelihood have a good effect, but it is opposite in slight training data. Besides, being independent with other speakers, we used training data for the same speaker to train speaker model owning to the method of maximum likelihood. In the stage of training model, we did not concern the relation of different speaker model, so we would get confused easily in speaker recognition. In recent years, Discriminative Acoustic Model Training is proposed to minimize classification error, not maximizing training acoustic models likelihood. In this thesis, we use minimum classification error to train speaker models, and support vector machines to improve minimum classification error. Due to the non-robustness of minimum classification error in setup for the amount of competitive speakers, we use the scores of speaker models for training data as labels of classes to train support vector machines. Then, we use support vectors to choose competitive speakers to make more robust and higher speaker recognition performance than minimum classification error.
