Iterative pseudo-forced alignment by acoustic CTC loss for self-supervised ASR domain adaptation
Paper
•
2210.15226
•
Published
Fernando López Gavilánez
ferugit
AI & ML interests
Speech Recognition, Audio classification, Keyword Spotting,
Recent Activity
liked
a model
3 days ago
DeSTA-ntu/DeSTA2.5-Audio-Llama-3.1-8B
liked
a Space
4 days ago
nvidia/audio-flamingo-3
liked
a model
18 days ago
BUT-FIT/diarizen-wavlm-large-s80-md
Organizations
authored
a
paper
almost 2 years ago