Search papers, labs, and topics across Lattice.
4
5
5
9
TurnBench reveals that human-like turn-taking in dialogue remains elusive for AI, with systems struggling to balance accuracy and false positives in interruption detection.
Dixtral achieves up to 29% absolute improvement in speaker-attributed transcription accuracy by leveraging diarization masks without risking catastrophic forgetting.
Anticipating dialogue endpoints up to 2.56 seconds ahead can slash latency by over half while enhancing computational efficiency in real-time speech interactions.
VAANI's open-sourced dataset offers unprecedented coverage of India's linguistic landscape, finally giving researchers the data needed to build truly inclusive speech models.
