Servicios Personalizados
Revista
Articulo
Indicadores
- Citado por SciELO
Links relacionados
- Similares en SciELO
Compartir
Latin American applied research
versión impresa ISSN 0327-0793versión On-line ISSN 1851-8796
Resumen
ALBORNOZ, E.M; MILONE, D.H; RUFINER, H.L y LOPEZ-COZAR, R. Classification of asr word hypotheses using prosodic information and resampling of training data. Lat. Am. appl. res. [online]. 2013, vol.43, n.3, pp.213-217. ISSN 0327-0793.
In this work, we propose a novel resampling method based on word lattice information and we use prosodic cues with support vector machines for classification. The idea is to consider word recognition as a two-class classification problem, which considers the word hypotheses in the lattice of a standard recognizer either as True or False employing prosodic information. The technique developed in this paper was applied to set of words extracted from a continuous speech database. Our experimental results show that the method allows obtaining average word hypotheses recognition rate of 82%
Palabras clave : Automatic Speech Recognition; Resampling Corpus; Support Vector Machines; Hypotheses Classification.