Search papers, labs, and topics across Lattice.
Affiliation:
5
0
3
7
Dialect recognition in ASR can be significantly improved without sacrificing Mandarin accuracy, thanks to a novel self-distillation approach.
Multi-speaker conversational understanding is critically under-evaluated, with MSU-Bench revealing that even leading models struggle with complex speaker grounding tasks.
Current spoken dialogue systems struggle with the nuances of human conversation, but a new benchmark offers a path to more natural interactions by focusing on handling interruptions and overlapping speech.
ALMs may ace the text, but HumDial-EIBench reveals they're shockingly bad at understanding the emotional nuances of real human conversations.
Achieve faster, more accurate turn-taking in spoken dialogue by fusing streaming speech recognition with raw audio cues – even when it's noisy.
