Multi-stream asynchrony dynamic Bayesian network model for audio-visual continuous speech recognition

Guoyun Lv; Dongmei Jiang; Rongchun Zhao; Xiaoyue Jiang; Hichem Sahli

Multi-stream asynchrony dynamic Bayesian network model for audio-visual continuous speech recognition

Guoyun Lv, Dongmei Jiang, Rongchun Zhao, Xiaoyue Jiang, Hichem Sahli

Onderzoeksoutput: Conference paper

1 Citaat (Scopus)

Samenvatting

Multi-stream asynchrony dynamic Bayesian network model for audio-visual continuous speech recognition

Originele taal-2	English
Titel	6th EURASIP Conference on Speech and Image Processing, Multimedia Communications and Services - EC-SIPMCS 2007
Pagina's	418-421
Aantal pagina's	4
Status	Published - 2007
Evenement	Unknown - Duur: 1 jan 2007 → …

Conference

Conference	Unknown
Periode	1/01/07 → …

1 Membership of external research organisation

Unknown (Externe Organisatie)
Hichem Sahli (Member)
20 dec 1999 → 31 dec 2003
Activiteit: Membership of external research organisation

Citeer dit

@inproceedings{2e3c07219cd940d8957e388da03b32ff,

title = "Multi-stream asynchrony dynamic Bayesian network model for audio-visual continuous speech recognition",

abstract = "Multi-stream asynchrony dynamic Bayesian network model for audio-visual continuous speech recognition",

keywords = "speech recognition, DBN",

author = "Guoyun Lv and Dongmei Jiang and Rongchun Zhao and Xiaoyue Jiang and Hichem Sahli",

year = "2007",

language = "English",

pages = "418--421",

booktitle = "6th EURASIP Conference on Speech and Image Processing, Multimedia Communications and Services - EC-SIPMCS 2007",

note = "null ; Conference date: 01-01-2007",

}

TY - GEN

T1 - Multi-stream asynchrony dynamic Bayesian network model for audio-visual continuous speech recognition

AU - Lv, Guoyun

AU - Jiang, Dongmei

AU - Zhao, Rongchun

AU - Jiang, Xiaoyue

AU - Sahli, Hichem

PY - 2007

Y1 - 2007

N2 - Multi-stream asynchrony dynamic Bayesian network model for audio-visual continuous speech recognition

AB - Multi-stream asynchrony dynamic Bayesian network model for audio-visual continuous speech recognition

KW - speech recognition

KW - DBN

M3 - Conference paper

SP - 418

EP - 421

BT - 6th EURASIP Conference on Speech and Image Processing, Multimedia Communications and Services - EC-SIPMCS 2007

Y2 - 1 January 2007

ER -

Multi-stream asynchrony dynamic Bayesian network model for audio-visual continuous speech recognition

Samenvatting

Conference

Vingerafdruk

Activiteiten

Unknown (Externe Organisatie)

Citeer dit