Open AccessNotes on the use of variational autoencoders for speech and audio spectrogram modeling
Author(s) -
Laurent Girin,
Fanny Roche,
Thomas Hueber,
Simon Leglaive
Publication year - 2019
Publication title -
hal (le centre pour la communication scientifique directe)
Language(s) - English
Resource type - Conference proceedings
Subject(s) - spectrogram , non negative matrix factorization , computer science , interpretability , speech recognition , representation (politics) , artificial intelligence , speech processing , matrix decomposition , artificial neural network , audio signal processing , pattern recognition (psychology) , audio signal , speech coding , eigenvalues and eigenvectors , physics , quantum mechanics , politics , political science , law