Cascaded encoders for fine-tuning ASR models on overlapped speech.

Richard Rose Oscar Chang Olivier Siohan

Published in: CoRR (2023)

Keyphrases

fine tuning
speech recognition
automatic speech recognition
spontaneous speech
fine tune
general purpose
statistical models
experimental data
spoken words
mathematical models
classification models
machine learning
statistical model
probabilistic model
face recognition
decision trees
computer vision