ShlokaDhara: A Multi-Speaker Sanskrit Speech Corpus for Learning Meter-Aware Prosody in Text-to-Recitation
This work establishes a robust dataset and evaluation benchmark for prosody-aware computational Sanskrit recitation by Benchmarking state-of-the-art TTS architectures via an automated UTMOS (neural MOS) predictor demonstrates that XTTS-v2 achieves the highest perceptual quality.
Harshal Kausadikar, O. Susladkar, Prathmesh Santosh Choudhari et al.
· 0 citations