Ircam-Centre Pompidou

Recherche

  • Recherche simple
  • Recherche avancée

    Panier électronique

    Votre panier ne contient aucune notice

    Connexion à la base

  • Identification
    (Identifiez-vous pour accéder aux fonctions de mise à jour. Utilisez votre login-password de courrier électronique)

    Entrepôt OAI-PMH

  • Soumettre une requête

    Consulter la notice détailléeConsulter la notice détaillée
    Version complète en ligneVersion complète en ligne
    Version complète en ligne accessible uniquement depuis l'IrcamVersion complète en ligne accessible uniquement depuis l'Ircam
    Ajouter la notice au panierAjouter la notice au panier
    Retirer la notice du panierRetirer la notice du panier

  • English version
    (full translation not yet available)
  • Liste complète des articles

    • Consultation des notices

    Vue détaillée Vue Refer Vue Labintel Vue BibTeX  

    %0 Conference Proceedings
    %A Obin, Nicolas
    %A Liuni, Marco
    %T On the Generalization of Shannon Entropy for Speech Recognition
    %D 2012
    %B IEEE workshop on Spoken Language Technology
    %C Miami
    %F Obin12e
    %K information theory
    %K spectral entropy
    %K speech recognition
    %K expressive speech
    %K voice quality
    %K video games
    %X This paper introduces an entropy-based spectral representation as a measure of the degree of noisiness in audio signals, complementary to the standard MFCCs for audio and speech recognition. The proposed representation is based on the Rényi entropy, which is a generalization of the Shannon entropy. In audio signal representation, Rényi entropy presents the advantage of focusing either on the harmonic content (prominent amplitude within a distribution) or on the noise content (equal distribution of amplitudes). The proposed representation outperforms all other noisiness measures - including Shannon and Wiener entropies - in a large-scale classification of vocal effort (whispered-soft/normal/loud-shouted) in the real scenario of multi-language massive role-playing video games. The improvement is around 10% in relative error reduction, and is particularly significant for the recognition of noisy speech - i.e., whispery/breathy speech. This confirms the role of noisiness for speech recognition, and will further be extended to the classification of voice quality for the design of an automatic voice casting system in video games.
    %1 6
    %2 1
    %U http://architexte.ircam.fr/textes/Obin12e/
    © Ircam - Centre Pompidou 2005.