Services on Demand
Journal
Article
Indicators
Cited by SciELO
Access statistics
Related links
Similars in SciELO
Share
Journal of applied research and technology
On-line version ISSN 2448-6736Print version ISSN 1665-6423
Abstract
MANTILLA-CAEIROS, A.; NAKANO-MIYATAKE, M. and PEREZ-MEANA, H.. A pattern recognition based esophageal speech enhancement system. J. appl. res. technol [online]. 2010, vol.8, n.1, pp.56-70. ISSN 2448-6736.
A system for improving the intelligibility and quality of alaryngeal speech based on the replacement of voiced segments of alaryngeal speech with the equivalent segments of normal speech is proposed. To this end, the system proposed identifies the voiced segments of the alaryngeal speech signal by using isolate speech recognition methods, and replaces them by their equivalent voiced segments of normal speech, keeping the silence and unvoiced segments without change. Evaluation results using objective and subjective evaluation methods show that the proposed system proposed provides a fairly good improvement of the quality and intelligibility of alaryngeal speech signals.
Keywords : Speech enhancement; esophageal speech; electronic larynx; multilayer perceptron; voiced and unvoiced segments detection; speech synthesis.