Research on Music Emotion Classification Based on the Feature Model of Emotion Category Contribution

Autor:	Wei Wu, Jin Zhong, Wen-Zhe Zhong
Rok vydání:	2018
Předmět:	Support vector machine ComputingMethodologies_PATTERNRECOGNITION Dimension (vector space) Computer science business.industry Emotion classification Feature extraction Vector space model Pattern recognition Artificial intelligence business Feature model Data modeling
Zdroj:	2018 International Conference on Big Data and Artificial Intelligence (BDAI).
DOI:	10.1109/bdai.2018.8546676
Popis:	There are problems in the text vector space model: the high dimension causes the sparsity of the vector space, the classification contribution is lower, and the classification accuracy, etc.The characteristic model for the contribution of special words to the emotion category is presented, An improved classification dimension decision fusion method based on the combination of audio features and lyrics features, Experimental results show that this method has good classification effect.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::b02cbbc9f46c02abe8ac7bfbd621aa74 https://doi.org/10.1109/bdai.2018.8546676 Zobrazit plný text záznamu