Cite
Notes
Only stored in your browser.
Attribution
ShiftySpeech: A Large-Scale Synthetic Speech Dataset with Distribution Shifts
arXiv 2025
DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition
arXiv 2024
Less Peaky and More Accurate CTC Forced Alignment by Label Priors
from 3 papers
Sanjeev Khudanpur
Alexander Polok
Ashi Garg
Bolaji Yusuf
Daniel Povey
Dominik Klement
Federico Landini
Henry Li Xinyuan
Jan Černocký
Jeff Hwang