Computational Pronunciation Analysis and Modeling of Sung Utterances » History » Version 1
Polina Proutskova, 2020-11-10 06:05 PM
| 1 | 1 | Polina Proutskova | h1. Computational Pronunciation Analysis and Modeling of Sung Utterances |
|---|---|---|---|
| 2 | 1 | Polina Proutskova | |
| 3 | 1 | Polina Proutskova | Emir Demirel |
| 4 | 1 | Polina Proutskova | |
| 5 | 1 | Polina Proutskova | 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. |