Search papers, labs, and topics across Lattice.
4
2
6
1
Synthetic data closes the Indic ASR gap where commercial and open-source systems fail, boosting entity recognition by up to 22x.
Speaker embeddings leak script information, especially when projecting Western voices into Indic scripts, but LASE fixes this with a language-adversarial training objective.
Achieve near-native Indic TTS from a non-Indic base model at zero commercial-training-data cost by cleverly combining phoneme space unification, LoRA adaptation, and voice-prompt recovery.
Commercial TTS systems nailing WER scores can still butcher Indic accents, especially retroflex articulation, and this new benchmark exposes exactly where they fail.
