A Generative Product-of-Filters Model of Audio

We propose the product-of-filters (PoF) model, a generative model that decomposes audio spectra as sparse linear combinations of "filters" in the log-spectral domain. PoF makes similar assumptions to those used in the classic homomorphic filtering approach to signal processing, but replace...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2014-11
Main Authors: Liang, Dawen, Hoffman, Matthew D, Mysore, Gautham J
Format: Article
Language:English
Subjects:
Algorithms
Decomposition
Feature extraction
Parameter estimation
Signal processing
Sound filters
Statistical inference
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose the product-of-filters (PoF) model, a generative model that decomposes audio spectra as sparse linear combinations of "filters" in the log-spectral domain. PoF makes similar assumptions to those used in the classic homomorphic filtering approach to signal processing, but replaces hand-designed decompositions built of basic signal processing operations with a learned decomposition based on statistical inference. This paper formulates the PoF model and derives a mean-field method for posterior inference and a variational EM algorithm to estimate the model's free parameters. We demonstrate PoF's potential for audio processing on a bandwidth expansion task, and show that PoF can serve as an effective unsupervised feature extractor for a speaker identification task.
ISSN:2331-8422