Login / Signup
On the use of Self-supervised Pre-trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition.
Manon Macary
Marie Tahon
Yannick Estève
Anthony Rousseau
Published in:
CoRR (2020)
Keyphrases
</>
linguistic features
pre trained
speech emotion recognition
named entities
structural features
training data
semantic features
text classification
training examples
linguistic knowledge
feature set
sentence level
part of speech
named entity recognition
news stories
translation model
machine learning
training set
computer vision
feature extraction
data sets
unsupervised learning
em algorithm
object recognition
clustering algorithm
control signals