Acoustic-Articulatory Modeling With the Trajectory HMM

Le Zhang, Steve Renals

Research output: Contribution to journalArticlepeer-review


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


  • Articulatory Inversion
  • trajectory hidden Markov model (HMM)


Dive into the research topics of 'Acoustic-Articulatory Modeling With the Trajectory HMM'. Together they form a unique fingerprint.

Cite this