Home » Conference Paper, Publication

Lyrics-to-Audio Alignment and Phrase-Level Segmentation Using Incomplete Internet-Style Chord Annotations

PDF BIBTEX   21 Juli 2010 1,352 views No Comment
Publication authored by Mauch, Matthias and Fujihara, Hiromasa and Goto, Masataka.

Abstract. We propose two novel lyrics-to-audio alignment methods which make use of additional chord information. In the first method we extend an existing hidden Markov model (HMM) for lyrics alignment by adding a chord model based on the chroma features often used in automatic audio chord detection. However, the textual transcriptions found on the Internet usually provide chords only for the first among all verses (or choruses, etc.). The second method we propose is therefore designed to work on these incom- plete transcriptions by finding a phrase-level segmenta- tion of the song using the partial chord information avail- able. This segmentation is then used to constrain the lyrics alignment. Both methods are tested against hand-labelled ground truth annotations of word beginnings. We use our first method to show that chords and lyrics complement each other, boosting accuracy from 59.1% (only chroma feature) and 46.0% (only phoneme feature) to 88.0% (0.51 seconds mean absolute displacement). Alignment perfor- mance decreases with incomplete chord annotations, but we show that our second method compensates for this in- formation loss and achieves an accuracy of 72.7%.

Bibtex
@inproceedings{mauch:laa:2010,
Author = {Matthias Mauch and Hiromasa Fujihara and Masataka Goto},
Booktitle = {Proceedings of the 7th Sound and Music Computing Conference (SMC 2010)},
Title = {Lyrics-to-Audio Alignment and Phrase-Level Segmentation Using Incomplete Internet-Style Chord Annotations},
Year = {2010}}

Comments are closed.