Euclidean distances between acoustic neighbor embeddings are interpreted as phonetic similarity through a Bayes-error and Gaussian-isotropy approximation, with four validation experiments.
Audio word2vec: Sequence-to-sequence autoencoding for unsupervised learn- ing of audio segmentation and representation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
A Theoretical Framework for Acoustic Neighbor Embeddings
Euclidean distances between acoustic neighbor embeddings are interpreted as phonetic similarity through a Bayes-error and Gaussian-isotropy approximation, with four validation experiments.