Throat microphone speech recognition using wav2vec 2.0 and feature mapping.

Kohta Masuda Jun Ogata Masafumi Nishida Masafumi Nishimura

Published in: GCCE (2022)

Keyphrases

feature mapping
automatic speech recognition
speech recognition
speaker diarization
manifold learning
speech signal
multiple instance learning
feature space
spam filtering
nonlinear dimensionality reduction
broadcast news
data sets
learning algorithm
training data
multi class
semi supervised