English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

L'accent est plac\'e dans cet article sur la structure hi\'erarchique,l'aspect parcimonieux de la repr\'esentation de l'information sonore, la tr\`esgrande dimension des caract\'eristiques ainsi que sur l'ind\'ependance descaract\'eristiques permettant de d\'efinir les composantes des objets sonores.Les notions d'objet sonore et de repr\'esentation neuronale sont d'abordintroduites, puis illustr\'ees avec une application en analyse de signauxsonores vari\'es: parole, musique et environnements naturels ext\'erieurs.Finalement, un nouveau syst\`eme de reconnaissance automatique de parole estpropos\'e. Celui-ci est compar\'e \`a un syst\`eme statistique conventionnel.Il montre tr\`es clairement que l'analyse par objets sonores introduit unegrande polyvalence et robustesse en reconnaissance de parole. Cetteint\'egration des connaissances en neurosciences et traitement des signauxacoustiques ouvre de nouvelles perspectives dans le domaine de lareconnaissance de signaux acoustiques.  The emphasis is put on the hierarchical structure, independence andsparseness aspects of auditory signal representations in high-dimensionalspaces, so as to define the components of auditory objects. The concept of anauditory object and its neural representation is introduced. An illustrativeapplication then follows, consisting in the analysis of various auditorysignals: speech, music and natural outdoor environments. A new automatic speechrecognition (ASR) system is then proposed and compared to a conventionalstatistical system. The proposed system clearly shows that an object-basedanalysis introduces a great flexibility and robustness for the task of speechrecognition. The integration of knowledge from neuroscience and acoustic signalprocessing brings new ways of thinking to the field of classification ofacoustic signals.

Objets Sonores: Une Repr\'esentation Bio-Inspir\'ee Hi\'erarchique  Parcimonieuse \`A Tr\`es Grandes Dimensions Utilisable En Reconnaissance;  Auditory Objects: Bio-Inspired Hierarchical Sparse High Dimensional  Representation for Recognition