Use of particle filtering and MCMC for inference in Probabilistic Acoustic Tube model

Ruobai Wang, Yang Zhang, Zhijian Ou, Mark Hasegawa-Johnson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The Probabilistic Acoustic Tube (PAT) model is a probabilistic generative model of speech. By associating every generative parameter with a probability distribution, it becomes possible to convert every standard speech analysis task into a probabilistic inference task, thereby grounding every such task with quantifiable measures of bias and consistency. The previously published PAT model did not adequately model AM-FM and therefore phase of the voice source. In this paper, we model the AM-FM of the voice source using an autoregressive process. The resulting model is a non-linear state-space model and thus has no closed-form inference algorithm, but effective inference can be achieved by using Auxiliary Particle Filtering (APF) and Taylor expansion assisted Markov Chain Monte Carlo (MCMC). Results demonstrate that, unlike previous speech models, this model is able to account for the phase of the voice source, achieving signal reconstruction with 8.79dB SNR.

Original languageEnglish (US)
Title of host publication2016 19th IEEE Statistical Signal Processing Workshop, SSP 2016
PublisherIEEE Computer Society
ISBN (Electronic)9781467378024
DOIs
StatePublished - Aug 24 2016
Externally publishedYes
Event19th IEEE Statistical Signal Processing Workshop, SSP 2016 - Palma de Mallorca, Spain
Duration: Jun 25 2016Jun 29 2016

Publication series

NameIEEE Workshop on Statistical Signal Processing Proceedings
Volume2016-August

Other

Other19th IEEE Statistical Signal Processing Workshop, SSP 2016
CountrySpain
CityPalma de Mallorca
Period6/25/166/29/16

Keywords

  • MCMC
  • Speech modeling
  • particle filter

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Applied Mathematics
  • Signal Processing
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Use of particle filtering and MCMC for inference in Probabilistic Acoustic Tube model'. Together they form a unique fingerprint.

  • Cite this

    Wang, R., Zhang, Y., Ou, Z., & Hasegawa-Johnson, M. (2016). Use of particle filtering and MCMC for inference in Probabilistic Acoustic Tube model. In 2016 19th IEEE Statistical Signal Processing Workshop, SSP 2016 [7551748] (IEEE Workshop on Statistical Signal Processing Proceedings; Vol. 2016-August). IEEE Computer Society. https://doi.org/10.1109/SSP.2016.7551748