A practical query-by-humming system for a large music database
A practical query-by-humming system for a large music database
复制标题
一个实用的大型音乐数据库哼唱查询系统
DOI：
10.1145/354384.354520
复制
发表时间：
2000
期刊：
影响因子：
--
通讯作者：
K. Kushima
中科院分区：
文献类型：
--
作者：
N. Kosugi;Yuichi Nishihara;Tetsuo Sakata;M. Yamamuro;K. Kushima
本文描述了一个音乐检索系统，接受哼唱曲调作为查询。该系统使用相似性检索，因为哼唱的曲调可能包含错误。检索结果是根据匹配的接近度排序的歌曲名称的列表。我们的最终目标是正确的歌曲应该在列表中的第一位。这意味着最终我们系统的相似性检索应该只允许一个正确答案。我们的系统与一般的哼唱查询系统相比，最重要的改进是所有音乐信息的处理都是基于节拍而不是音符。这种类型的查询处理对于由错误输入生成的查询是鲁棒的。此外，声学信息被转录并转换成相对间隔，并用于制作特征向量。与仅使用俯仰方向信息的其他一般系统相比，这增加了检索系统的分辨率。数据库目前拥有超过10，000首歌曲，检索时间最多为一秒。这种性能水平主要是通过使用索引进行检索来实现的。在本文中，我们还报告了数据库中的歌曲的音乐分析的结果。在此基础上，提出了部分特征向量和多关键字间艾德检索等提高检索精度的新技术。对这些技术的有效性进行了定量评估，发现与以前的系统相比，检索精度提高了20%以上[9]。还描述了系统的实际用户界面。
A music retrieval system that accepts hummed tunes as queries is described in this paper. This system uses similarity retrieval because a hummed tune may contain errors. The retrieval result is a list of song names ranked according to the closeness of the match. Our ultimate goal is that the correct song should be first on the list. This means that eventually our system's similarity retrieval should allow for only one correct answer. The most significant improvement our system has over general query-by-humming systems is that all processing of musical information is done based on beats instead of notes. This type of query processing is robust against queries generated from erroneous input. In addition, acoustic information is transcribed and converted into relative intervals and is used for making feature vectors. This increases the resolution of the retrieval system compared with other general systems, which use only pitch direction information. The database currently holds over 10,000 songs, and the retrieval time is at most one second. This level of performance is mainly achieved through the use of indices for retrieval. In this paper, we also report on the results of music analyses of the songs in the database. Based on these results, new technologies for improving retrieval accuracy, such as partial feature vectors and or'ed retrieval among multiple search keys, are proposed. The effectiveness of these technologies is evaluated quantitatively, and it is found that the retrieval accuracy increases by more than 20% compared with the previous system [9]. Practical user interfaces for the system are also described.