Prosody Prediction
3 papers with code • 1 benchmarks • 2 datasets
Predicting prosodic prominence from text. This is a 2-way classification task, assigning each word in a sentence a label 1 (prominent) or 0 (non-prominent).
( Image credit: Helsinki Prosody Corpus )
Benchmarks
These leaderboards are used to track progress in Prosody Prediction
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Helsinki Prosody Corpus
CANDOR Corpus
Most implemented papers
Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations
Helsinki-NLP/prosody
•
•
WS (NoDaLiDa) 2019
In this paper we introduce a new natural language processing dataset and benchmark for predicting prosodic prominence from written text.
On the Utility of Self-supervised Models for Prosody-related Tasks
jsalt-2022-ssl/superb-prosody
•
•
We find that 13 of the 15 SSL models outperformed the baseline on all the prosody-related tasks.
PRESENT: Zero-Shot Text-to-Prosody Control
We attain 25. 3% hanzi CER and 13. 0% pinyin CER with the JETS model.
