Skip to main content

Models of Speech: In Search of Better Representations

This special issue originates from a special session at the international conference Interspeech, which was held in September 2010 at Chiba, Japan. It will publish some key contributions presented at the conference describing different aspects of models of speech, from the analyisis or representation point of view.

Edited by: Hideki Kawahara and Hansjörg Mixdorff

  1. The full modulation spectrum is a high-dimensional representation of one-dimensional audio signals. Most previous research in automatic speech recognition converted this very rich representation into the equiv...

    Authors: Sara Ahmadi, Seyed Mohammad Ahadi, Bert Cranen and Lou Boves
    Citation: EURASIP Journal on Audio, Speech, and Music Processing 2014 2014:36
  2. Model-based speech enhancement algorithms that employ trained models, such as codebooks, hidden Markov models, Gaussian mixture models, etc., containing representations of speech such as linear predictive coef...

    Authors: Devireddy Hanumantha Rao Naidu and Sriram Srinivasan
    Citation: EURASIP Journal on Audio, Speech, and Music Processing 2014 2014:35
  3. The current paper examines influences of speech rate on Fujisaki model parameters based on read speech from the BonnTempo-Corpus containing productions by 12 native speakers of German at five different intende...

    Authors: Hansjörg Mixdorff, Adrian Leemann and Volker Dellwo
    Citation: EURASIP Journal on Audio, Speech, and Music Processing 2014 2014:33
  4. This paper proposes two novel approaches for parameter estimation of a superpositional intonation model. These approaches present linguistic and paralinguistic assumptions for initializing a pre-existing stand...

    Authors: Humberto M Torres, Jorge A Gurlekian, Hansjörg Mixdorff and Hartmut Pfitzinger
    Citation: EURASIP Journal on Audio, Speech, and Music Processing 2014 2014:28
  5. This paper investigates the estimation of underlying articulatory targets of Thai vowels as invariant representation of vocal tract shapes by means of analysis-by-synthesis based on acoustic data. The basic id...

    Authors: Santitham Prom-on, Peter Birkholz and Yi Xu
    Citation: EURASIP Journal on Audio, Speech, and Music Processing 2014 2014:23