Quantification of the anatomic and functional aspects of the tongue is pertinent to analyse the mechanisms involved in speech production. Speech requires dynamic and complex articulation of the vocal tract organs, and the tongue is one of the main articulators during speech production. Magnetic resonance imaging has been widely used in speech-related studies. Moreover, the segmentation of such images of speech organs is required to extract reliable statistical data. However, standard solutions to analyse a large set of articulatory images have not yet been established. Therefore, this article presents an approach to segment the tongue in two-dimensional magnetic resonance images and statistically model the segmented tongue shapes. The proposed approach assesses the articulator morphology based on an active shape model, which captures the shape variability of the tongue during speech production. To validate this new approach, a dataset of mid-sagittal magnetic resonance images acquired from four subjects was used, and key aspects of the shape of the tongue during the vocal production of relevant European Portuguese vowels were evaluated.
MunhallKG. Functional imaging during speech production. Acta Psychol2001; 107: 95–117.
2.
LevineWTorcasoCStoneM. Controlling the shape of a muscular hydrostat: a tongue or tentacle. In: DayawansaWPLindquistAZhouY (eds) New directions and applications in control theory (Lecture notes control, vol. 321). Berlin, Heidelberg: Springer, 2005, pp.207–222.
3.
CootesTFTaylorCJCooperDHet al. Active shape models-their training and application. Comput Vis Image Und1995; 61: 38–59.
4.
VenturaSMRVasconcelosMJMFreitasDRSet al. Speaker-specific articulatory assessment and measurements during Portuguese speech production based on magnetic resonance images. In: WarfeltLM (ed.) Language acquisition: gazelle. New York: Nova Science Publishers, 2012, pp.117–138.
5.
MillerNAGregoryJSAspdenRMet al. Using active shape modeling based on MRI to study morphologic and pitch-related functional changes affecting vocal structures and the airway. J Voice2014; 28: 554–564.
6.
MartinsPOliveiraCSilvaSet al. Tongue segmentation from MRI images using ITK-SNAP: preliminary evaluation. In: Proceedings of the IADIS International Conference Computer Graphics, Visualization, Computer Vision and Image Processing , (ed XiaoY.), Rome, Italy, 20–26 July 2011, pp. 3-10, ISBN: 978-972-8939-48-9.
7.
SoniesBC. Ultrasonic visualization of tongue motion during speech. J Acoust Soc Am1981; 70: 683–686.
8.
ThimmG. Tracking articulators in X-ray movies of the vocal tract. In: Proceedings of the 8th international conference on computer analysis of images and patterns, Ljubljana, 1–3 September 1999, pp.126–133. Berlin, Heidelberg: Springer.
9.
HavyMBouchonCNazziT. Phonetic processing when learning words: the case of bilingual infants. Int J Behav Dev2016; 40: 41–52.
10.
TakemotoHHondaKMasakiSet al. Measurement of temporal changes in vocal tract area function from 3D cine-MRI data. J Acoust Soc Am2006; 119: 1037–1049.
11.
PengTKerrienEBergerMO. A shape-based framework to segmentation of tongue contours from MRI data. In: Proceedings of the 2010 IEEE international conference on acoustics, speech and signal processing (ICASSP), Dallas, TX, 14–19 March 2010, pp.662–665. New York: IEEE.
12.
Rua VenturaSMFreitasDRSRamosIMAPet al. Morphologic differences in the vocal tract resonance cavities of voice professionals: an MRI-based study. J Voice2013; 27: 132–140.
13.
ZhangDYangMTaoJet al. Extraction of tongue contour in real-time magnetic resonance imaging sequences. In: Proceedings of the 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP), Shanghai, China, 20–25 March 2016, pp.937–941. New York: IEEE.
14.
VasconcelosMJVenturaSMFreitasDRet al. Inter-speaker speech variability assessment using statistical deformable models from 3.0 Tesla magnetic resonance images. Proc IMechE, Part H: J Engineering in Medicine2012; 226: 185–196.
15.
BadinPSerrurierA. Three-dimensional linear modeling of tongue: articulatory data and models. In: Proceedings of the 7th international seminar on speech production (ISSP7), Ubatuba, Brazil, 13–15 December 2006, pp.395–402. Belo Horizonte, Brazil: UFMG.
16.
EryildirimABergerMO. A guided approach for automatic segmentation and modeling of the vocal tract in MRI images. In: Proceedings of the 19th European signal processing conference, Barcelona, 29 August–2 September 2011, pp.61–65. New York: IEEE.
17.
SongCWeiJFangQet al. Tongue shape synthesis based on Active Shape Model. In: Proceedings of the international symposium on Chinese spoken language processing, Kowloon, China, 5–8 December 2012, pp.383–386. New York: IEEE.
18.
EttaïebSHamrouniKRuanS. Statistical models of shape and spatial relation-application to hippocampus segmentation. In: Proceedings of the 2014 international conference on computer vision theory and applications (VISAPP), Lisbon, 5–8 January 2014, pp.448–455. New York: IEEE.
19.
ElBazMSFahmyAS. Active shape model with inter-profile modeling paradigm for cardiac right ventricle segmentation. In: Proceedings of the 15th international conference on medical image computing and computer-assisted intervention (MICCAI 2012), Nice, 1–5 October 2012, pp.691–698. Berlin, Heidelberg: Springer.
20.
VasconcelosMJMVenturaSMRTavaresJMRSet al. Analysis of tongue shape and motion in speech production using statistical modeling. In: Proceedings of the 2nd South-East European Conference on Computational Mechanics (eds PapadopoulosV.PapadrakakisM.KojicM.), Island of Rhodes, Greece, 22–24 June 2009 pp. 96–8, ISBN: 978-960-254-683-3.
21.
Tristán-VegaAGarcía-PérezVAja-FernándezSet al. Efficient and robust nonlocal means denoising of MR data based on salient features matching. Comput Meth Prog Bio2012; 105: 131–144.
22.
CootesTFTaylorCJ. Active shape models –‘smart snakes’. London: Springer, 1992.
23.
GhesuFCKrubasikEGeorgescuBet al. Marginal space deep learning: efficient architecture for volumetric image parsing. IEEE T Med Imaging2016; 35: 1217–1228.
