Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition
Srijith Radhakrishnan, Chao-Han Huck Yang, Sumeer Ahmad Khan, Rohit Kumar, Narsis A. Kiani, David Gomez-Cabrero, Jesper Tegnér
Main: Speech & Multimodality 2 Main-oral Paper
Session 10: Speech & Multimodality 2 (Oral)
Conference Room: West 1
Conference Time: December 10, 11:00-12:30 (+08) (Asia/Singapore)
Global Time: December 10, Session 10 (03:00-04:30 UTC)
TLDR:
You can open the
#paper-4032
channel in a separate window.
Abstract: