IndicFDB: Benchmarking Full-Duplex Voice Agents across Indian Languages
This work addresses three challenges: finding conversational events in multilingual speech, evaluating their timing without reliable word-level alignment, and judging responses across languages with IndicFDB, which extends it to ten languages spoken in India with 12,350 samples.
Rajarshi Roy, Shobhit Banga, Jonathan Raiman et al.
· 1 citation