Marathi

The 'Marathi' dataset/benchmark is used to evaluate the performance of multilingual automatic speech recognition (ASR) systems, specifically in the context of comparing different projector designs across multiple Indic languages.

Papers using Marathi (3)

Factors affecting ASR performance: A study using state of the art ASR models in Indic Languages2026Dynamic Multi-Expert Projectors with Stabilized Routing for Multilingual Speech Recognition2026VECL-TTS: Voice identity and Emotional style controllable Cross-Lingual Text-to-Speech2024