Use of Multi-Layered Networks for Coding Speech with Phonetic Features (Contributo in volume (capitolo o saggio))

Type

• Prodotto della ricerca (Classe)
• Contributo in volume (capitolo o saggio) (Classe)

Label

• Use of Multi-Layered Networks for Coding Speech with Phonetic Features (Contributo in volume (capitolo o saggio)) (literal)

Anno

• 1989-01-01T00:00:00+01:00 (literal)

Alternative label

• Bengio Y., Cardin R., Cosi P., De Mori R. (1989)
  Use of Multi-Layered Networks for Coding Speech with Phonetic Features
  MORGAN KAUFMANN, Palo Alto (Stati Uniti d'America) in Advances in Neural Information Processing Systems, 1989
  (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori

• Bengio Y., Cardin R., Cosi P., De Mori R. (literal)

Pagina inizio

• 224 (literal)

Pagina fine

• 231 (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#altreInformazioni

• Bengio Y., Cardin R., Cosi P., De Mori R. Use of Multi-Layered Networks for Coding Speech with Phonetic Features in Advances in Neural Information Processing Systems 1 D.S. Touretzky editor Morgan Kaufmann Publisher 1989 http://books.nips.cc/papers/files/nips01/0224.pdf http://www2.pd.istc.cnr.it/Papers/PieroCosi/cp-NIPS89.pdf pages 224-231. (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#url

• http://books.nips.cc/papers/files/nips01/0224.pdf (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#titoloVolume

• Advances in Neural Information Processing Systems (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#volumeInCollana

• 1 (literal)

Note

• ACM DL (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni

• ISTC CNR, UOS Padova Cosi P. Computer Science Departement, Mc Gill University, Montreal Quebec, CANADA Bengio Y., Cardin R.,De Mori R. (literal)

Titolo

• Use of Multi-Layered Networks for Coding Speech with Phonetic Features (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#isbn

• 1-558-60015-9 (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#curatoriVolume

• D.S. Touretzky (literal)

Abstract

• Preliminary results on speaker-independant speech recognition are reported. A method that combines expertise on neural networks with expertise on speech recognition is used to build the recognition systems. For transient sounds, event-driven property extractors with variable resolution in the time and frequency domains are used. For sonorant speech, a model of the human auditory system is preferred to FFT as a front-end module. (literal)

Editore

• MORGAN KAUFMANN (Editore)

Prodotto di

• Parlato e Comunicazione Multimodale (IC.P02.008.001) (Modulo)
• Institute of cognitive sciences and technologies (ISTC) (Istituto)

Autore CNR

• PIERO COSI (Persona)

Insieme di parole chiave

• Keywords of "Use of Multi-Layered Networks for Coding Speech with Phonetic Features" (Insieme di parole chiave)

Incoming links:

Autore CNR di

• PIERO COSI (Persona)

Prodotto

• Institute of cognitive sciences and technologies (ISTC) (Istituto)
• Parlato e Comunicazione Multimodale (IC.P02.008.001) (Modulo)

Editore di

• MORGAN KAUFMANN (Editore)

Insieme di parole chiave di

• Keywords of "Use of Multi-Layered Networks for Coding Speech with Phonetic Features" (Insieme di parole chiave)