Speech classification using SIFT features on spectrogram images

详细信息    查看全文

• 作者：Quang Trung Nguyen ; The Duy Bui
• 关键词：LNBNN ; SIFT ; Speech perception ; Speech classification
• 刊名：Vietnam Journal of Computer Science
• 出版年：2016
• 出版时间：November 2016
• 年：2016
• 卷：3
• 期：4
• 页码：247-257
• 全文大小：1,418 KB
• 刊物类别：Information Systems and Communication Service; Artificial Intelligence (incl. Robotics); Computer Ap
• 刊物主题：Information Systems and Communication Service; Artificial Intelligence (incl. Robotics); Computer Applications; e-Commerce/e-business; Computer Systems Organization and Communication Networks; Computa
• 出版者：Springer Berlin Heidelberg
• ISSN：2196-8896
• 卷排序：3

文摘

Classification of speech is one of the most vital problems in speech processing. Although there have been many studies on the classification of speech, the results are still limited. Firstly, most of the speech classification approaches requiring input data have the same dimension. Secondly, all traditional methods must be trained before classifying speech signal and must be retrained when having more training data or new class. In this paper, we propose an approach for speech classification using Scale-invariant Feature Transform (SIFT) features on spectrogram images of speech signal combination with Local naïve Bayes nearest neighbor. The proposed approach allows using feature vectors to have different sizes. With this approach, the achieved classification results are satisfactory. They are 73, 96, 95, 97 %, and 97 % on the ISOLET, English Isolated Digits, Vietnamese Places, Vietnamese Digits, JVPD databases, respectively. Especially, in a subset of the TMW database, the accuracy is 100 %. In addition, in our proposed approach, non-retraining is needed for additional training data after the training phase. The experiment shows that the more features are added to the model, the more is the accuracy in performance.