Pascal and Francis Bibliographic Databases

Help

Export

Selection :

Permanent link
http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=18526259

Reducing computation time of the rapid unsupervised speaker adaptation based on HMM-sufficient statistics

Author
GOMEZ, Randy1 ; TODA, Tomoki1 ; SARUWATARI, Hiroshi1 ; SHIKANO, Kiyohiro1
[1] Nara Institute of Science and Technology, Ikoma-shi, 630-0192, Japan
Source

IEICE transactions on information and systems. 2007, Vol 90, Num 2, pp 554-561, 8 p ; ref : 18 ref

ISSN
0916-8532
Scientific domain
Electronics; Computer science; Telecommunications
Publisher
Oxford University Press, Oxford
Publication country
United Kingdom
Document type
Article
Language
English
Author keyword
HMM-sufficient statistics rapid adaptation speech recognition unsupervised
Keyword (fr)
Adaptation locuteur Approche probabiliste Bruit fond Canal vocal Classification non supervisée Classification signal Estimation a posteriori Evaluation performance Hors ligne Implémentation Interpolation linéaire Maximum vraisemblance Modèle Markov variable cachée Performance algorithme Rapport signal bruit Reconnaissance parole Régression linéaire Temps calcul Traitement parole
Keyword (en)
Speaker adaptation Probabilistic approach Background noise Vocal tract Unsupervised classification Signal classification A posteriori estimation Performance evaluation Off line Implementation Linear interpolation Maximum likelihood Hidden Markov models Algorithm performance Signal to noise ratio Speech recognition Linear regression Computation time Speech processing
Keyword (es)
Adaptación locutor Enfoque probabilista Ruido fondo Conducto vocal Clasificación no supervisada Estimación a posteriori Evaluación prestación Fuera linea Implementación Interpolación lineal Maxima verosimilitud Resultado algoritmo Relación señal ruido Reconocimiento voz Regresión lineal Tiempo computación Tratamiento palabra
Classification
Pascal
001 Exact sciences and technology / 001D Applied sciences / 001D02 Computer science; control theory; systems / 001D02C Artificial intelligence / 001D02C04 Speech and sound recognition and synthesis. Linguistics

Pascal
001 Exact sciences and technology / 001D Applied sciences / 001D04 Telecommunications and information theory / 001D04A Information, signal and communications theory / 001D04A04 Signal and communications theory / 001D04A04A Signal, noise / 001D04A04A1 Signal representation. Spectral analysis

Pascal
001 Exact sciences and technology / 001D Applied sciences / 001D04 Telecommunications and information theory / 001D04A Information, signal and communications theory / 001D04A05 Signal processing / 001D04A05B Speech processing

Discipline
Computer science : theoretical automation and systems Telecommunications and information theory
Origin
Inist-CNRS
Database
PASCAL
INIST identifier
18526259

Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS

Access to the document

Searching the Web