{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T04:13:52Z","timestamp":1749096832876,"version":"3.41.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319401737"},{"type":"electronic","value":"9783319401744"}],"license":[{"start":{"date-parts":[[2016,8,6]],"date-time":"2016-08-06T00:00:00Z","timestamp":1470441600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-40174-4_4","type":"book-chapter","created":{"date-parts":[[2016,8,5]],"date-time":"2016-08-05T06:21:15Z","timestamp":1470378075000},"page":"51-71","source":"Crossref","is-referenced-by-count":0,"title":["Combining Modalities: Multimodal SSI"],"prefix":"10.1007","author":[{"given":"Jo\u00e3o","family":"Freitas","sequence":"first","affiliation":[]},{"given":"Ant\u00f3nio","family":"Teixeira","sequence":"additional","affiliation":[]},{"given":"Miguel Sales","family":"Dias","sequence":"additional","affiliation":[]},{"given":"Samuel","family":"Silva","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,8,6]]},"reference":[{"key":"4_CR1","volume-title":"Visual speech recognition for European Portuguese, M.Sc. thesis","author":"H Abreu","year":"2014","unstructured":"Abreu H (2014) Visual speech recognition for European Portuguese, M.Sc. thesis. University of Minho, Portugal"},{"key":"4_CR2","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1109\/34.927467","volume":"23","author":"TF Cootes","year":"2001","unstructured":"Cootes TF, Edwards GJ, Taylor CJ (2001) Active appearance models. IEEE Trans Pattern Anal Mach Intell 23:681\u2013685. doi: 10.1109\/34.927467","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4_CR3","doi-asserted-by":"publisher","DOI":"10.1002\/047174882X","volume-title":"Elements of information theory","author":"TM Cover","year":"2005","unstructured":"Cover TM, Thomas JA (2005) Elements of information theory. Wiley, New York. doi: 10.1002\/047174882X"},{"key":"4_CR4","unstructured":"Denby, B (2013. Down with Sound, the Story of Silent Speech. In: Workshop on Speech production in automatic speech recognition"},{"key":"4_CR5","doi-asserted-by":"publisher","unstructured":"Denby B, Stone, M (2004) Speech synthesis from real time ultrasound images of the tongue. 2004 IEEE Int. Conf. Acoust. Speech, Signal Process. 1. doi: 10.1109\/ICASSP.2004.1326078","DOI":"10.1109\/ICASSP.2004.1326078"},{"key":"4_CR6","doi-asserted-by":"crossref","first-page":"1316","DOI":"10.1016\/j.neuropsychologia.2012.02.016","volume":"50","author":"C Dubois","year":"2012","unstructured":"Dubois C, Otzenberger H, Gounot D, Sock R, Metz-Lutz M-N (2012) Visemic processing in audiovisual discrimination of natural speech: a simultaneous fMRI\u2013EEG study. Neuropsychologia 50:1316\u20131326","journal-title":"Neuropsychologia"},{"key":"4_CR7","doi-asserted-by":"publisher","first-page":"1794","DOI":"10.1016\/j.patrec.2012.05.019","volume":"33","author":"A Ferreira","year":"2012","unstructured":"Ferreira A, Figueiredo M (2012) Efficient feature selection filters for high-dimensional data. Pattern Recognit Lett 33:1794\u20131804. doi: 10.1016\/j.patrec.2012.05.019","journal-title":"Pattern Recognit Lett"},{"key":"4_CR8","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1111\/j.1469-1809.1936.tb02137.x","volume":"7","author":"RA Fisher","year":"1936","unstructured":"Fisher RA (1936) The use of multiple measurements in taxonomic problems. Ann Hum Genet 7:179\u2013188. doi: 10.1111\/j.1469-1809.1936.tb02137.x","journal-title":"Ann Hum Genet"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Florescu VM, Crevier-Buchman L, Denby B, Hueber T, Colazo-Simon A, Pillot-Loiseau C, Roussel-Ragot P, Gendrot C, Quattrocchi S (2010) Silent vs vocalized articulation for a portable ultrasound-based silent speech interface. In: Proceedings of Interspeech 2010, pp 450\u2013453","DOI":"10.21437\/Interspeech.2010-195"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Freitas J, Teixeira A, Dias MS (2012a) Towards a silent speech interface for Portuguese: surface electromyography and the nasality challenge. In: International conference on bio-inspired systems and signal processing (BIOSIGNALS 2012), pp 91\u2013100","DOI":"10.5220\/0003786100910100"},{"key":"4_CR11","doi-asserted-by":"publisher","unstructured":"Freitas J, Teixeira A, Vaz F, Dias MS (2012b) Automatic speech recognition based on ultrasonic doppler sensing for European Portuguese. In: Advances in speech and language technologies for Iberian languages, communications in computer and information science. Springer, Berlin, pp 227\u2013236. doi: 10.1007\/978-3-642-35292-8_24","DOI":"10.1007\/978-3-642-35292-8_24"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Freitas J, Ferreira A, Figueiredo M, Teixeira A, Dias MS (2014a) Enhancing multimodal silent speech interfaces with feature selection. In: 15th Annual Conf. of the Int. Speech Communication Association (Interspeech 2014), Singapore, pp. 1169\u20131173","DOI":"10.21437\/Interspeech.2014-297"},{"key":"4_CR13","unstructured":"Freitas J, Teixeira A, Dias MS (2014b) Multimodal corpora for silent speech interaction. In: 9th Language resources and evaluation conference, pp 1\u20135"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Freitas J, Teixeira A, Silva S, Oliveira C, Dias MS (2014c) Assessing the applicability of surface EMG to tongue gesture detection. In: Proceedings of IberSPEECH 2014, lecture notes in artificial intelligence (LNAI). Springer, Berlin, pp 189\u2013198","DOI":"10.1007\/978-3-319-13623-3_20"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Freitas J, Teixeira A, Silva S, Oliveira C, Dias MS (2014d) Velum movement detection based on surface electromyography for speech interface. In: International conference on bio-inspired systems and signal processing (BIOSIGNALS 2014), pp 13\u201320","DOI":"10.5220\/0004741100130020"},{"key":"4_CR16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0127040","volume":"10","author":"J Freitas","year":"2015","unstructured":"Freitas J, Teixeira A, Silva S, Oliveira C, Dias MS (2015) Detecting nasal vowels in speech interfaces based on surface electromyography. PLoS One 10, e0127040. doi: 10.1371\/journal.pone.0127040","journal-title":"PLoS One"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Galatas G, Potamianos G, Makedon F (2012a) Audio-visual speech recognition incorporating facial depth information captured by the Kinect. In: 20th European signal processing conference, pp 2714\u20132717","DOI":"10.1145\/2413097.2413100"},{"key":"4_CR18","doi-asserted-by":"publisher","unstructured":"Galatas G, Potamianos G, Makedon F (2012b) Audio-visual speech recognition using depth information from the kinect in noisy video condition. In: Proceedings of the 5th International conference on pervasive technologies related to assistive environments\u2014PETRA\u201912, pp 1\u20134. doi: 10.1145\/2413097.2413100","DOI":"10.1145\/2413097.2413100"},{"key":"4_CR19","doi-asserted-by":"publisher","first-page":"4765","DOI":"10.1109\/TSP.2009.2026513","volume":"57","author":"M Gurban","year":"2009","unstructured":"Gurban M, Thiran J-P (2009) Information theoretic feature extraction for audio-visual speech recognition. IEEE Trans Signal Process 57:4765\u20134776. doi: 10.1109\/TSP.2009.2026513","journal-title":"IEEE Trans Signal Process"},{"key":"4_CR190","doi-asserted-by":"crossref","unstructured":"Hofe R, Bai J, Cheah LA, Ell SR, Gilbert JM, Moore RK, Green PD (2013) Performance of the MVOCA silent speech interface across multiple speakers. In: Proc. of Interspeech, 2013, pp. 1140\u20131143","DOI":"10.21437\/Interspeech.2013-311"},{"key":"4_CR20","doi-asserted-by":"publisher","DOI":"10.1121\/1.421133","author":"JF Holzrichter","year":"1998","unstructured":"Holzrichter JF, Burnett GC, Ng LC, Lea WA (1998) Speech articulator measurements using low power EM-wave sensors. J Acoust Soc Am. doi: 10.1121\/1.421133","journal-title":"J Acoust Soc Am"},{"key":"4_CR21","volume-title":"Articulate assistant advanced ultrasound module user manual, Revision 212","author":"Instruments, A","year":"2014","unstructured":"Instruments, A (2014) Articulate assistant advanced ultrasound module user manual, Revision 212. Articulate Instruments, Edinburgh"},{"key":"4_CR22","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1109\/LSP.2007.896450","volume":"14","author":"K Kalgaonkar","year":"2007","unstructured":"Kalgaonkar K, Hu RHR, Raj B (2007) Ultrasonic Doppler sensor for voice activity detection. IEEE Signal Proc Lett 14:754\u2013757. doi: 10.1109\/LSP.2007.896450","journal-title":"IEEE Signal Proc Lett"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Lahr RJ (2006) Head-worn, trimodal device to increase transcription accuracy in a voice recognition system and to process unvocalized speech. US 7082393 B2","DOI":"10.1121\/1.2434335"},{"key":"4_CR230","doi-asserted-by":"crossref","unstructured":"Narayanan S, Bresch E, Ghoosh P, Goldstein L, Katsamanis A, Kim Y, Lammert AC, Proctor M, Ramanarayanan V, Zhu Y (2011) A multimodal real-time MRI articulatory corpus for speech research. In: Proc. Interspeech, 2011, pp. 837\u2013840","DOI":"10.21437\/Interspeech.2011-308"},{"key":"4_CR24","volume-title":"Discrete time signal processing","author":"AV Oppenheim","year":"1999","unstructured":"Oppenheim AV, Schafer RW, Buck JR (1999) Discrete time signal processing. Prentice-Hall, Upper Saddle River"},{"key":"4_CR25","unstructured":"Plux Wireless Biosignals (n.d.) www.plux.info\/ . Accessed 30 October 2014"},{"key":"4_CR26","doi-asserted-by":"crossref","first-page":"1306","DOI":"10.1109\/JPROC.2003.817150","volume":"91","author":"G Potamianos","year":"2003","unstructured":"Potamianos G, Neti C, Gravier G, Garg A, Senior AW (2003) Recent advances in the automatic recognition of audiovisual speech. Proc IEEE 91:1306\u20131326","journal-title":"Proc IEEE"},{"key":"4_CR27","unstructured":"Scobbie JM, Wrench AA, van der Linden M (2008) Head-probe stabilisation in ultrasound tongue imaging using a headset to permit natural head movement. In: Proceedings of the 8th International seminar on speech production, pp 373\u2013376"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Silva S, Teixeira A (2014) Automatic annotation of an ultrasound corpus for studying tongue movement. In: Proc. ICIAR, LNCS 8814. Springer, Vilamoura, pp. 469\u2013476","DOI":"10.1007\/978-3-319-11758-4_51"},{"key":"4_CR29","doi-asserted-by":"publisher","unstructured":"Srinivasan S, Raj B, Ezzat T (2010) Ultrasonic sensing for robust speech recognition. In: IEEE int. conf. on acoustics, speech and signal processing (ICASSP 2010). doi: 10.1109\/ICASSP.2010.5495039","DOI":"10.1109\/ICASSP.2010.5495039"},{"key":"4_CR290","doi-asserted-by":"publisher","unstructured":"Stone M, Lundberg A (1996) Three-dimensional tongue surface shapes of English consonants and vowels. J Acoust Soc Am 99:3728\u20133737. doi: 10.1121\/1.414969","DOI":"10.1121\/1.414969"},{"key":"4_CR30","doi-asserted-by":"crossref","first-page":"656","DOI":"10.21437\/Interspeech.2009-230","volume":"2009","author":"V-A Tran","year":"2009","unstructured":"Tran V-A, Bailly G, L\u0153venbruck H, Toda T (2009) Multimodal HMM-based NAM-to-speech conversion. Interspeech 2009:656\u2013659","journal-title":"Interspeech"},{"key":"4_CR31","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1016\/j.specom.2009.11.005","volume":"52","author":"VA Tran","year":"2010","unstructured":"Tran VA, Bailly G, Loevenbruck H, Toda T (2010) Improvement to a NAM-captured whisper-to-speech system. Speech Commun 52:314\u2013326. doi: 10.1016\/j.specom.2009.11.005","journal-title":"Speech Commun"},{"key":"4_CR32","unstructured":"Wand M, Schultz T (2011) Session-independent EMG-based Speech Recognition. In: International conference on bio-inspired systems and signal processing (BIOSIGNALS 2011), pp 295\u2013300"},{"key":"4_CR33","doi-asserted-by":"publisher","unstructured":"Yau WC, Arjunan SP, Kumar DK (2008) Classification of voiceless speech using facial muscle activity and vision based techniques. TENCON 2008\u20132008 IEEE Reg. 10 Conf. doi: 10.1109\/TENCON.2008.4766822","DOI":"10.1109\/TENCON.2008.4766822"}],"container-title":["SpringerBriefs in Electrical and Computer Engineering","An Introduction to Silent Speech Interfaces"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-40174-4_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T15:06:56Z","timestamp":1749049616000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-40174-4_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8,6]]},"ISBN":["9783319401737","9783319401744"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-40174-4_4","relation":{},"ISSN":["2191-8112","2191-8120"],"issn-type":[{"type":"print","value":"2191-8112"},{"type":"electronic","value":"2191-8120"}],"subject":[],"published":{"date-parts":[[2016,8,6]]}}}