2 papers
cs.CL2025
Kinship in Speech: Leveraging Linguistic Relatedness for Zero-Shot TTS in Indian Languages
Utkarsh Pathak, Chandra Sai Krishna Gunda, Anusha Prakash +2
Text-to-speech (TTS) systems typically require high-quality studio data and accurate transcriptions for training. India has 1369 languages, with 22 official using 13 scripts. Train…
eess.AS2024
A Unified Framework for Collecting Text-to-Speech Synthesis Datasets for 22 Indian Languages
Sujitha Sathiyamoorthy, N Mohana, Anusha Prakash +1
The performance of a text-to-speech (TTS) synthesis model depends on various factors, of which the quality of the training data is of utmost importance. Millions of data are collec…