# Computational Pronunciation Analysis in Sung Utterances

arXiv: https://arxiv.org/abs/2106.10977 · HTML: https://mlsanity.com/paper/2106.10977/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jun 2021.

## Built on by (most cited first, 2 of 2)

- [MSTRE-Net: Multistreaming Acoustic Modeling for Automatic Lyrics Transcription](https://mlsanity.com/paper/2108.02625/) (2021)
- [Towards Building an End-to-End Multilingual Automatic Lyrics Transcription Model](https://mlsanity.com/paper/2406.17618/) (2024)

## Abstract (arXiv)

Recent automatic lyrics transcription (ALT) approaches focus on building stronger acoustic models or in-domain 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 sentence-level annotations used in testing, providing a new benchmark evaluation set for ALT.