RepLyal: REPetitive-based LYric ALigner

[ Back to the WING home page ]

This is the home page of the RepLyal project in which we examine the problem of automatically aligning acoustic musical audio and textual lyric in popular songs. Existing works have tackled the problem using computationally-expensive audio processing techniques, resulting in solutions unsuitable for real-time application. In contrast, our work features only lightweight signal processing, and mainly focuses on repetition-based techniques as well as alignment algorithms to allow real-time performance.

System overview

Demonstration

You can pick up any out of 30 songs in the dataset listed below for the system to perform alignment. The automatic annotation will be displayed in synchronization with the corresponding audio file.

References

• Wang Ye, Min-Yen Kan, Tin Lay Nwe, Arun Shenoy and Jun Yin (2004) LyricAlly: Automatic Synchronization of Acoustic Musical Signals and Textual Lyrics . In Proceedings of ACM Multimedia 2004 (MM '04), New York, USA, 10-16 October. [ .pdf ]
• Luong Minh Thang and Min-Yen Kan (2007) A repetition-based framework for lyric alignment in popular songs. National University of Singapore Department of Computer Science - NUROP paper. [ .pdf ]
• Luong Minh Thang and Min-Yen Kan (2007) A repetition-based framework for lyric alignment in popular songs. National University of Singapore Department of Computer Science - Detailed UROP report. [ .pdf ]

Group Members

• Min-Yen Kan - Project leader
• Luong Minh Thang - UROP student

Luong Minh Thang <minh_thang@nus.edu.sg>

Created on: Wed Dec 5 16:07:15 2007 | Version: 1.0 | Last modified: Wed Dec 5 16:07:15 2007