Papers by Preeti Rao

2 papers
STORiCo: Storytelling TTS for Hindi with Character Voice Modulation (2024.eacl-short)

Copied to clipboard

Challenge: Existing datasets for read speech for Hindi lack expressiveness and character voice consistency.
Approach: They propose to use a Hindi text-to-speech (TTS) dataset to train a multi-speaker model on the single-sector data and propose to improve expressiveness and character voice consistency.
Outcome: The proposed model improves expressiveness and character voice consistency compared to the baseline single-speaker model.
Predicting Prosodic Boundaries for Children’s Texts (2025.emnlp-main)

Copied to clipboard

Challenge: Using a dataset of 54 leveled English stories annotated for potential pauses, we find that nearly 30% of pause occur at non-punctuation locations of the text.
Approach: They propose to use a text-based model to predict pause locations in children's reading material using a curated dataset of 54 leveled English stories annotated for potential pauses, or prosodic boundaries, by 21 fluent speakers.
Outcome: The proposed model can model both allowed and “forbidden” pauses . it uses a curated dataset of 54 leveled English stories annotated for potential pause locations by 21 fluent speakers .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations