We propose a Multigranular Automatic Speech Recognizer. The hypothesis is that speech signal contains information distributed on more different time scales. Many works from various scientific fields ranging from neurobiology to speech technologies, seem to concord on this assumption. In a broad sense, it seems that speech recognition in human is optimal because of a partial parallelization process according to which the left-to-right stream of speech is captured in a multilevel grid in which several linguistic analyses take place contemporarily. Our investigation aims, in this view, to apply these new ideas to the project of more robust and efficient recognizers.

Multigranular scale speech recognition: tehnological and cognitive view / Cutugno, Francesco; Coro, G; Petrillo, M.. - STAMPA. - 3673:(2005), pp. 327-330. (Intervento presentato al convegno AI*IA20054 tenutosi a Milano nel 23-25 settembre 2005).

Multigranular scale speech recognition: tehnological and cognitive view

CUTUGNO, FRANCESCO;
2005

Abstract

We propose a Multigranular Automatic Speech Recognizer. The hypothesis is that speech signal contains information distributed on more different time scales. Many works from various scientific fields ranging from neurobiology to speech technologies, seem to concord on this assumption. In a broad sense, it seems that speech recognition in human is optimal because of a partial parallelization process according to which the left-to-right stream of speech is captured in a multilevel grid in which several linguistic analyses take place contemporarily. Our investigation aims, in this view, to apply these new ideas to the project of more robust and efficient recognizers.
2005
Multigranular scale speech recognition: tehnological and cognitive view / Cutugno, Francesco; Coro, G; Petrillo, M.. - STAMPA. - 3673:(2005), pp. 327-330. (Intervento presentato al convegno AI*IA20054 tenutosi a Milano nel 23-25 settembre 2005).
File in questo prodotto:
File Dimensione Formato  
5.pdf

accesso aperto

Tipologia: Documento in Post-print
Licenza: Dominio pubblico
Dimensione 126.85 kB
Formato Adobe PDF
126.85 kB Adobe PDF Visualizza/Apri
abs1.txt

non disponibili

Tipologia: Abstract
Licenza: Accesso privato/ristretto
Dimensione 684 B
Formato Text
684 B Text   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11588/102343
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact