New Method for Classification of ASR Word Hypotheses Using Prosodic Cues

ENRIQUE M. ALBORNOZ; DIEGO H. MILONE; HUGO L. RUFINER; RAMÓN LÓPEZ-CÓZAR

Oro Verde - Entre Ríos

Congreso; XIV Reunión de Trabajo en Procesamiento de la Información y Control; 2011

Facultad de Ingeniería - Universidad Nacional de Entre Ríos

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 isto 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%.