The use of phonetic motor invariants can improve automatic phoneme discrimination.

We investigate the use of phonetic motor invariants (MIs), that is, recurring kinematic patterns of the human phonetic articulators, to improve automatic phoneme discrimination. Using a multi-subject database of synchronized speech and lips/tongue trajectories, we first identify MIs commonly associa...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Claudio Castellini, Leonardo Badino, Giorgio Metta, Giulio Sandini, Michele Tavella, Mirko Grimaldi, Luciano Fadiga
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2011
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/41573dd36f3241e7bca75951cba3e20c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:41573dd36f3241e7bca75951cba3e20c
record_format	dspace
spelling	oai:doaj.org-article:41573dd36f3241e7bca75951cba3e20c2021-11-18T06:46:46ZThe use of phonetic motor invariants can improve automatic phoneme discrimination.1932-620310.1371/journal.pone.0024055https://doaj.org/article/41573dd36f3241e7bca75951cba3e20c2011-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/21912661/?tool=EBIhttps://doaj.org/toc/1932-6203We investigate the use of phonetic motor invariants (MIs), that is, recurring kinematic patterns of the human phonetic articulators, to improve automatic phoneme discrimination. Using a multi-subject database of synchronized speech and lips/tongue trajectories, we first identify MIs commonly associated with bilabial and dental consonants, and use them to simultaneously segment speech and motor signals. We then build a simple neural network-based regression schema (called Audio-Motor Map, AMM) mapping audio features of these segments to the corresponding MIs. Extensive experimental results show that (a) a small set of features extracted from the MIs, as originally gathered from articulatory sensors, are dramatically more effective than a large, state-of-the-art set of audio features, in automatically discriminating bilabials from dentals; (b) the same features, extracted from AMM-reconstructed MIs, are as effective as or better than the audio features, when testing across speakers and coarticulating phonemes; and dramatically better as noise is added to the speech signal. These results seem to support some of the claims of the motor theory of speech perception and add experimental evidence of the actual usefulness of MIs in the more general framework of automated speech recognition.Claudio CastelliniLeonardo BadinoGiorgio MettaGiulio SandiniMichele TavellaMirko GrimaldiLuciano FadigaPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 6, Iss 9, p e24055 (2011)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Claudio Castellini Leonardo Badino Giorgio Metta Giulio Sandini Michele Tavella Mirko Grimaldi Luciano Fadiga The use of phonetic motor invariants can improve automatic phoneme discrimination.
description	We investigate the use of phonetic motor invariants (MIs), that is, recurring kinematic patterns of the human phonetic articulators, to improve automatic phoneme discrimination. Using a multi-subject database of synchronized speech and lips/tongue trajectories, we first identify MIs commonly associated with bilabial and dental consonants, and use them to simultaneously segment speech and motor signals. We then build a simple neural network-based regression schema (called Audio-Motor Map, AMM) mapping audio features of these segments to the corresponding MIs. Extensive experimental results show that (a) a small set of features extracted from the MIs, as originally gathered from articulatory sensors, are dramatically more effective than a large, state-of-the-art set of audio features, in automatically discriminating bilabials from dentals; (b) the same features, extracted from AMM-reconstructed MIs, are as effective as or better than the audio features, when testing across speakers and coarticulating phonemes; and dramatically better as noise is added to the speech signal. These results seem to support some of the claims of the motor theory of speech perception and add experimental evidence of the actual usefulness of MIs in the more general framework of automated speech recognition.
format	article
author	Claudio Castellini Leonardo Badino Giorgio Metta Giulio Sandini Michele Tavella Mirko Grimaldi Luciano Fadiga
author_facet	Claudio Castellini Leonardo Badino Giorgio Metta Giulio Sandini Michele Tavella Mirko Grimaldi Luciano Fadiga
author_sort	Claudio Castellini
title	The use of phonetic motor invariants can improve automatic phoneme discrimination.
title_short	The use of phonetic motor invariants can improve automatic phoneme discrimination.
title_full	The use of phonetic motor invariants can improve automatic phoneme discrimination.
title_fullStr	The use of phonetic motor invariants can improve automatic phoneme discrimination.
title_full_unstemmed	The use of phonetic motor invariants can improve automatic phoneme discrimination.
title_sort	use of phonetic motor invariants can improve automatic phoneme discrimination.
publisher	Public Library of Science (PLoS)
publishDate	2011
url	https://doaj.org/article/41573dd36f3241e7bca75951cba3e20c
work_keys_str_mv	AT claudiocastellini theuseofphoneticmotorinvariantscanimproveautomaticphonemediscrimination AT leonardobadino theuseofphoneticmotorinvariantscanimproveautomaticphonemediscrimination AT giorgiometta theuseofphoneticmotorinvariantscanimproveautomaticphonemediscrimination AT giuliosandini theuseofphoneticmotorinvariantscanimproveautomaticphonemediscrimination AT micheletavella theuseofphoneticmotorinvariantscanimproveautomaticphonemediscrimination AT mirkogrimaldi theuseofphoneticmotorinvariantscanimproveautomaticphonemediscrimination AT lucianofadiga theuseofphoneticmotorinvariantscanimproveautomaticphonemediscrimination AT claudiocastellini useofphoneticmotorinvariantscanimproveautomaticphonemediscrimination AT leonardobadino useofphoneticmotorinvariantscanimproveautomaticphonemediscrimination AT giorgiometta useofphoneticmotorinvariantscanimproveautomaticphonemediscrimination AT giuliosandini useofphoneticmotorinvariantscanimproveautomaticphonemediscrimination AT micheletavella useofphoneticmotorinvariantscanimproveautomaticphonemediscrimination AT mirkogrimaldi useofphoneticmotorinvariantscanimproveautomaticphonemediscrimination AT lucianofadiga useofphoneticmotorinvariantscanimproveautomaticphonemediscrimination
_version_	1718424409496092672

The use of phonetic motor invariants can improve automatic phoneme discrimination.

Ejemplares similares