Music Information Retrieval from a Singing Voice Using Lyrics and Melody Information. (6th December 2006)

• Record Type: Journal Article
• Authors: Suzuki Suzuki, Motoyuki Motoyuki; Hosoya Hosoya, Toru Toru; Ito Ito, Akinori Akinori; Makino Makino, Shozo Shozo
• Other Names: Goto Goto Masataka Masataka Academic Editor.
• Is Part Of: EURASIP journal on advances in signal processing. Volume 2007(2007)
• Publication Date: 2006-12-06
• Subjects: Signal processing -- Periodicals; Traitement du signal; Signal processing; Periodicals; 621.3822
• DOI: 10.1155/2007/38727
• Languages: English
• ISSNs: 1687-6172

Abstract

Abstract : Recently, several music information retrieval (MIR) systems which retrieve musical pieces by the user's singing voice have been developed. All of these systems use only melody information for retrieval, although lyrics information is also useful for retrieval. In this paper, we propose a new MIR system that uses both lyrics and melody information. First, we propose a new lyrics recognition method. A finite state automaton (FSA) is used as recognition grammar, and about86 % retrieval accuracy was obtained. We also develop an algorithm for verifying a hypothesis output by a lyrics recognizer. Melody information is extracted from an input song using several pieces of information of the hypothesis, and a total score is calculated from the recognition score and the verification score. From the experimental results, 95.0% retrieval accuracy was obtained with a query consisting of five words.