Detail publikace

The subspace Gaussian mixture model-A structured model for speech recognition

POVEY, D. BURGET, L. AGARWAL, M. AKYAZI, P. GHOSHAL, A. GLEMBEK, O. GOEL, N. KARAFIÁT, M. RASTROW, A. ROSE, R. SCHWARZ, P. THOMAS, S.

Originální název

The subspace Gaussian mixture model-A structured model for speech recognition

Typ

článek v časopise ve Web of Science, Jimp

Jazyk

angličtina

Originální abstrakt

Speech recognition based on the Hidden Markov Model-Gaussian Mixture Model (HMM-GMM) framework generally involves training a completely separate GMM in each HMM state.We introduce a model in which the HMM states share a common structure but the means and mixture weights are allowed to vary in a subspace of the full parameter space, controlled by a global mapping from a vector space to the space of GMM parameters.

Klíčová slova

Speech recognition; Gaussian Mixture Model; Subspace Gaussian Mixture Model

Autoři

POVEY, D.; BURGET, L.; AGARWAL, M.; AKYAZI, P.; GHOSHAL, A.; GLEMBEK, O.; GOEL, N.; KARAFIÁT, M.; RASTROW, A.; ROSE, R.; SCHWARZ, P.; THOMAS, S.

Rok RIV

2011

Vydáno

1. 4. 2011

Nakladatel

Elsevier Science

ISSN

0885-2308

Periodikum

COMPUTER SPEECH AND LANGUAGE

Ročník

25

Číslo

2

Stát

Spojené království Velké Británie a Severního Irska

Strany od

404

Strany do

439

Strany počet

36

URL

BibTex

@article{BUT76383,
  author="Daniel {Povey} and Lukáš {Burget} and Mohit {Agarwal} and Pinar {Akyazi} and Arnab {Ghoshal} and Ondřej {Glembek} and Nagendra {Goel} and Martin {Karafiát} and Ariya {Rastrow} and Richard {Rose} and Petr {Schwarz} and Samuel {Thomas}",
  title="The subspace Gaussian mixture model-A structured model for speech recognition",
  journal="COMPUTER SPEECH AND LANGUAGE",
  year="2011",
  volume="25",
  number="2",
  pages="404--439",
  issn="0885-2308",
  url="https://www.fit.vut.cz/research/publication/9670/"
}