A second opinion approach for speech recognition verification
Document typeConference report
PublisherM,I, Torres & A. Sanfeliu / AERFAI
Rights accessOpen Access
In order to improve the reliability of speech recognition results, a verifying system, that takes profit of the information given from an alternative recognition step is proposed. The alternative results are considered as a second opinion about the nature of the speech recognition process. Some features are extracted from both opinion sources and compiled, through a fuzzy inference system, into a more discriminant confidence measure able to verify correct results and disregard wrong ones. This approach is tested in a keyword spotting task taken form the Spanish SpeechDat database. Results show a considerable reduction of false rejections at a fixed false alarm rate compared to baseline systems.
CitationHernández-Ábrego, G., Mariño, J.B. A second opinion approach for speech recognition verification. A: Simposium Nacional de Reconocimiento de Formas y Análisis de Imágenes. "Proceedings of the VIII National Symposium on Pattern Recognition and Image Analysis.". Bilbao: M,I, Torres & A. Sanfeliu / AERFAI, 1999, p. 85-92.