Computational Pronunciation Analysis in Sung Utterances
View/ Open
Publisher
DOI
10.48550/arxiv.2106.10977
Journal
arXiv
Metadata
Show full item recordAbstract
Recent automatic lyrics transcription (ALT) approaches focus on building stronger acoustic models or indomain language models, while the pronunciation aspect is
seldom touched upon. This paper applies a novel computational
analysis on the pronunciation variances in sung utterances
and further proposes a new pronunciation model adapted for
singing. The singing-adapted model is tested on multiple public
datasets via word recognition experiments. It performs better
than the standard speech dictionary in all settings reporting
the best results on ALT in a capella recordings using n-gram
language models. For reproducibility, we share the sentencelevel annotations used in testing, providing a new benchmark
evaluation set for ALT.