III-COR-Small: Bootstrapping Adaptive Personalized Music Search with Game-based Collaborative Tagging

III-COR-Small：通过基于游戏的协作标记引导自适应个性化音乐搜索

• 批准号: 0812314
• 负责人: Bryan Pardo
• 金额: $ 44.42万
• 依托单位: Northwestern University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2008
• 资助国家: 美国
• 起止时间: 2008-09-01 至 2012-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0812314&HistoricalAwards=false
• 关键词: III; COR; Small; Bootstrapping; Adaptive

This proposal addresses novel ways of indexing large music databases programmatically. It proposes to use melody, rhythm, and to some extent lyrics to index musical databases. The PI proposes to build a search engine for music that takes sung examples as input for searching relevant songs. The search engine adapts to individual needs through feedback and ongoing personalization to improve the search results. Finding ways to automatically index, label, and access multimedia content (such as music documents) is a research question that is increasing in importance as multimedia databases proliferate and grow.

这个提议提出了以编程方式索引大型音乐数据库的新方法。它建议使用旋律、节奏，并在一定程度上使用歌词来索引音乐数据库。PI建议建立一个音乐搜索引擎，将歌曲示例作为搜索相关歌曲的输入。搜索引擎通过反馈和持续的个性化来适应个人需求，从而改进搜索结果。寻找自动索引、标记和访问多媒体内容（如音乐文档）的方法是一个研究问题，随着多媒体数据库的激增和增长，这个问题的重要性日益增加。