Modeling speech with sum-product networks: Application to bandwidth extension

Robert Peharz, Georg Kapeller, Pejman Mowlaee, Franz PernkopfICASSP 2014 · OpenReview

Abstract

Sum-product networks (SPNs) are a recently proposed type of probabilistic graphical models allowing complex variable interactions while still granting efficient inference. In this paper we demonstrate the suitability of SPNs for modeling log-spectra of speech signals using the application of artificial bandwidth extension, i.e. artificially replacing the high-frequency content which is lost in telephone signals. We use SPNs as observation models in hidden Markov models (HMMs), which model the temporal evolution of log short-time spectra. Missing frequency bins are replaced by the SPNs using most-probable-explanation inference, where the state-dependent reconstructions are weighted with the HMM state posterior. According to subjective listening and objective evaluation, our system consistently and significantly improves the state of the art.
BibTeX
@inproceedings{peharz2014modeling,
  author = {Robert Peharz and Georg Kapeller and Pejman Mowlaee and Franz Pernkopf},
  title = {{Modeling speech with sum-product networks: Application to bandwidth extension}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2014},
  url = {https://openreview.net/forum?id=JbsgtiqGeLC},
}

Loading related content...

Figure