Detail výsledku

Neural network topologies and bottle neck features in speech recognition

GRÉZL, F.; KARAFIÁT, M.; ČERNOCKÝ, J. Neural network topologies and bottle neck features in speech recognition. Brno: 2007. p. 78-82.
Typ
prezentace, poster
Jazyk
anglicky
Autoři
Grézl František, Ing., Ph.D., UPGM (FIT)
Karafiát Martin, Ing., Ph.D., UPGM (FIT)
Černocký Jan, prof. Dr. Ing., UPGM (FIT)
Abstrakt

Different neural net topologies for estimating features for speechrecognition were presented. We introduced bottle-neck structure intopreviously proposed Split Context. This was done mainly to reduce sizeof resulting neural net, which serves as feature estimator. Whenbottle-neck outputs are used also as final outputs from neural networkinstead of probability estimates, the reduction of word error rate isalso reached.

Klíčová slova

neural networks, topologies, speech recognition, bottle-neck features

URL
Rok
2007
Strany
78–82
Konference
Machine Learning and Multimodal Interaction
Místo
Brno
BibTeX 
@misc{BUT63689,
  author="František {Grézl} and Martin {Karafiát} and Jan {Černocký}",
  title="Neural network topologies and bottle neck features in speech recognition",
  year="2007",
  pages="78--82",
  address="Brno",
  url="http://www.fit.vutbr.cz/~grezl/publi/mlmi2007.pdf"
}
Projekty
Nové směry ve výzkumu a využití hlasových technologií, GAČR, Standardní projekty, GA102/05/0278, zahájení: 2005-01-01, ukončení: 2007-12-31, ukončen
Výzkumné skupiny
Výzkumná skupina dolování dat z řeči BUT Speech@FIT (VZ SPEECH)
Pracoviště
Ústav počítačové grafiky a multimédií (UPGM)
Nahoru