Acoustic and emotion embeddings reduce EER for vocal expression detection by 60% and 30% relative to bag-of-words and acoustic baselines.
The data had neither any speaker level information nor any contextual information: every query was independent of every other
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Leveraging Acoustic Cues and Paralinguistic Embeddings to Detect Expression from Voice
Acoustic and emotion embeddings reduce EER for vocal expression detection by 60% and 30% relative to bag-of-words and acoustic baselines.