Edinburgh Research Explorer

Acoustic-Articulatory Modeling With the Trajectory HMM

Research output: Contribution to journalArticle

Original languageEnglish
Pages (from-to)245-248
Number of pages4
JournalIEEE Signal Processing Letters
Volume15
DOIs
Publication statusPublished - 8 Feb 2008

Abstract

Abstract:
In this letter, we introduce an hidden Markov model (HMM)-based inversion system to recovery articulatory movements from speech acoustics. Trajectory HMMs are used as generative models for modelling articulatory data. Experiments on the MOCHA-TIMIT corpus indicate that the jointly trained acoustic-articulatory models are more accurate (lower RMS error) than the separately trained ones, and that trajectory HMM training results in greater accuracy compared with conventional maximum likelihood HMM training. Moreover, the system has the ability to synthesize articulatory movements directly from a textual representation.

    Research areas

  • Articulatory Inversion , MOCHA-TIMIT, trajectory hidden Markov model (HMM)

Download statistics

No data available

ID: 111867