Differentiable Measures for Speech Spectral Modeling

Differentiable Measures for Speech Spectral Modeling

Autoregressive models for the envelope of speech power spectral densities (PSDs) are refined by the self-supervised spectral learning machine (S3LM) provided with differentiable spectral objective functions, including the Itakura-Saito divergence (ISD), the Kullback-Leibler divergence (KLD), the rev...

Full description

Bibliographic Details
Main Authors: Miguel Arjona Ramirez, Wesley Beccaro, Demostenes Zegarra Rodriguez, Renata Lopes Rosa
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Autoregressive processes
machine learning algorithms
prediction methods
self-supervised learning
speech analysis
spectral analysis
Online Access:https://ieeexplore.ieee.org/document/9709279/

Similar Items

Similar Items