Autoregressive Models for Statistical Parametric Speech Synthesis

M. Shannon, Heiga Zen, W. Byrne

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

We propose using the autoregressive hidden Markov model (HMM) for speech synthesis. The autoregressive HMM uses the same model for parameter estimation and synthesis in a consistent way, in contrast to the standard approach to statistical parametric speech synthesis. It supports easy and efficient parameter estimation using expectation maximization, in contrast to the trajectory HMM. At the same time its similarities to the standard approach allow use of established high quality synthesis algorithms such as speech parameter generation considering global variance. The autoregressive HMM also supports a speech parameter generation algorithm not available for the standard approach or the trajectory HMM and which has particular advantages in the domain of real-time, low latency synthesis. We show how to do efficient parameter estimation and synthesis with the autoregressive HMM and look at some of the similarities and differences between the standard approach, the trajectory HMM and the autoregressive HMM. We compare the three approaches in subjective and objective evaluations. We also systematically investigate which choices of parameters such as autoregressive order and number of states are optimal for the autoregressive HMM.
Original languageEnglish
Pages (from-to)587-597
Number of pages11
JournalIEEE Transactions on Audio, Speech and Language Processing
Issue number3
Publication statusPublished - 2013

Keywords / Materials (for Non-textual outputs)

  • hidden Markov models
  • speech synthesis
  • statistical analysis
  • autoregressive HMM model
  • autoregressive hidden Markov model
  • autoregressive order
  • expectation maximization
  • global variance
  • high quality synthesis algorithms
  • parameter estimation
  • speech parameter generation algorithm
  • statistical parametric speech synthesis
  • Acoustics
  • Hidden Markov models
  • Parameter estimation
  • Speech
  • Speech synthesis
  • Standards
  • Vectors
  • Acoustic modeling
  • autoregressive processes
  • hidden Markov models (HMMs)
  • speech


Dive into the research topics of 'Autoregressive Models for Statistical Parametric Speech Synthesis'. Together they form a unique fingerprint.

Cite this