|Title:||Articulatory Feature Extraction from Voice and Their Impact on Hybrid Acoustic Models||Authors:||Llombart, Jorge
|UNESCO Clasification:||220990 Tratamiento digital. Imágenes||Keywords:||Articulatory features
|Issue Date:||2014||Publisher:||Springer||Journal:||Lecture Notes in Computer Science||Abstract:||There is a great amount of information in the speech signal, although current speech recognizers do not exploit it completely. In this paper articulatory information is extracted from speech and fused to standard acoustic models to obtain a better hybrid acoustic model which provides improvements on speech recognition. The paper also studies the best input signal for the system in terms of type of speech features and time resolution to obtain a better articulatory information extractor. Then this information is fused to a standard acoustic model obtained with neural networks to perform the speech recognition achieving better results.||URI:||http://hdl.handle.net/10553/53701||ISBN:||978-3-319-13622-6||ISSN:||0302-9743||DOI:||10.1007/978-3-319-13623-3_15||Source:||Advances in Speech and Language Technologies for Iberian Languages. Lecture Notes in Computer Science, v. 8854 LNCS, p. 138-147|
|Appears in Collections:||Capítulo de libro|
WEB OF SCIENCETM
checked on Jul 25, 2021
checked on Jul 24, 2021
Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.