HMM-Based Speech Synthesis Utilizing Glottal Inverse Filtering

T. Raitio, A. Suni, J. Yamagishi, H. Pulakka, J. Nurminen, M. Vainio, P. Alku

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

This paper describes an hidden Markov model (HMM)-based speech synthesizer that utilizes glottal inverse filtering for generating natural sounding synthetic speech. In the proposed method, speech is first decomposed into the glottal source signal and the model of the vocal tract filter through glottal inverse filtering, and thus parametrized into excitation and spectral features. The source and filter features are modeled individually in the framework of HMM and generated in the synthesis stage according to the text input. The glottal excitation is synthesized through interpolating and concatenating natural glottal flow pulses, and the excitation signal is further modified according to the spectrum of the desired voice source characteristics. Speech is synthesized by filtering the reconstructed source signal with the vocal tract filter. Experiments show that the proposed system is capable of generating natural sounding speech, and the quality is clearly better compared to two HMM-based speech synthesis systems based on widely used vocoder techniques.
Original languageEnglish
Pages (from-to)153-165
Number of pages13
JournalIEEE Transactions on Audio, Speech and Language Processing
Issue number1
Publication statusPublished - Jan 2011

Keywords / Materials (for Non-textual outputs)

  • interpolating natural glottal flow pulses
  • Electrical capacitance tomography
  • concatenating natural glottal flow pulses
  • spectral features
  • glottal inverse filtering
  • glottal source signal reconstruction
  • hidden Markov models
  • Speech synthesis
  • Character generation
  • Postal services
  • vocal tract filter
  • glottal excitation signal
  • signal reconstruction
  • Vocoders
  • hidden Markov model (HMM)
  • hidden Markov model
  • Filtering
  • vocoder techniques
  • natural sounding synthetic speech
  • HMM-based speech synthesis
  • Filters
  • Signal synthesis
  • Hidden Markov models
  • speech synthesis
  • Glottal inverse filtering
  • Helium


Dive into the research topics of 'HMM-Based Speech Synthesis Utilizing Glottal Inverse Filtering'. Together they form a unique fingerprint.

Cite this