Music Emotion Recognition Using Two Level Classification
محل انتشار: دوازدهمین کنفرانس ملی سیستم های هوشمند ایران
سال انتشار: 1392
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 869
فایل این مقاله در 6 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ICS12_182
تاریخ نمایه سازی: 11 مرداد 1393
چکیده مقاله:
Rapid growth of digital music data in the Internet during the recent years has led to increase of user demands for search based on different types of meta data. One kind of metadata that we focused in this paper is the emotion or mood of music. Music emotion recognition is a prevalent research topictoday. We collected a database including 280 pieces of popular music with four basic emotions of Thayer's two Dimensionalmodel. We used a two level classifier the process of which couldbe briefly summarized in three steps: 1) Extracting most suitable features from pieces of music in the database to describe eachmusic song; 2) Applying feature selection approaches to decrease correlations between features; 3) Using SVM classifier in twolevel to train these features. Finally we increased accuracy rate from 72.14% with simple SVM to 87.27% with our hierarchical classifier.
کلیدواژه ها:
نویسندگان
Samira Pouyanfar,
Department of Computer Engineering Sharif University of Technology, Tehran, Iran
Hossein Sameti
Department of Computer Engineering Sharif University of Technology, Tehran, Iran