Query by humming: musical information retrieval in an audio database
Proceedings of the third ACM international conference on Multimedia
A practical query-by-humming system for a large music database
MULTIMEDIA '00 Proceedings of the eighth ACM international conference on Multimedia
Super MBox: an efficient/effective content-based music retrieval system
MULTIMEDIA '01 Proceedings of the ninth ACM international conference on Multimedia
A comparison of melodic database retrieval techniques using sung queries
Proceedings of the 2nd ACM/IEEE-CS joint conference on Digital libraries
Analysis of Vowels in Sung Queries for a Music Information Retrieval System
Journal of Intelligent Information Systems
A comprehensive trainable error model for sung music queries
Journal of Artificial Intelligence Research
An effective music information retrieval method using three-dimensional continuous DP
IEEE Transactions on Multimedia
Finding `Lucy in Disguise': The Misheard Lyric Matching Problem
AIRS '09 Proceedings of the 5th Asia Information Retrieval Symposium on Information Retrieval Technology
Automatic recognition of lyrics in singing
EURASIP Journal on Audio, Speech, and Music Processing - Special issue on atypical speech
Hybrid query by humming and metadata search system (HQMS)
Proceedings of the 8th International Conference on Frontiers of Information Technology
A query by humming system based on locality sensitive hashing indexes
Signal Processing
IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)
Hi-index | 0.00 |
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 about 86% 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.