Advances in phonetics-based sub-unit modeling for transcription alignment and sign language recognition

Pitsikalis, V; Theodorakis, S; Vogler, C; Maragos, P

dc.contributor.author	Pitsikalis, V	en
dc.contributor.author	Theodorakis, S	en
dc.contributor.author	Vogler, C	en
dc.contributor.author	Maragos, P	en
dc.date.accessioned	2014-03-01T02:47:16Z
dc.date.available	2014-03-01T02:47:16Z
dc.date.issued	2011	en
dc.identifier.issn	21607508	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/33045
dc.subject	Feature Extraction	en
dc.subject	Sign Language	en
dc.subject	Sign Language Recognition	en
dc.subject	Speech Recognition	en
dc.subject	Statistical Model	en
dc.subject	Visual Features	en
dc.subject	Greek Sign Language	en
dc.subject	Hidden Markov Model	en
dc.subject	Pure Data	en
dc.subject.other	Automatic recognition	en
dc.subject.other	Boundary information	en
dc.subject.other	Data-driven approach	en
dc.subject.other	Phonetic transcriptions	en
dc.subject.other	Sign language	en
dc.subject.other	Sign Language recognition	en
dc.subject.other	Statistical models	en
dc.subject.other	Structured sequence	en
dc.subject.other	Sub-units	en
dc.subject.other	Symbolic processing	en
dc.subject.other	Visual data	en
dc.subject.other	Visual feature	en
dc.subject.other	Computer vision	en
dc.subject.other	Transcription	en
dc.subject.other	Linguistics	en
dc.title	Advances in phonetics-based sub-unit modeling for transcription alignment and sign language recognition	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/CVPRW.2011.5981681	en
heal.identifier.secondary	http://dx.doi.org/10.1109/CVPRW.2011.5981681	en
heal.identifier.secondary	5981681	en
heal.publicationDate	2011	en
heal.abstract	We explore novel directions for incorporating phonetic transcriptions into sub-unit based statistical models for sign language recognition. First, we employ a new symbolic processing approach for converting sign language annotations, based on HamNoSys symbols, into structured sequences of labels according to the Posture-Detention-Transition-Steady Shift phonetic model. Next, we exploit these labels, and their correspondence with visual features to construct phonetics-based statistical sub-unit models. We also align these sequences, via the statistical sub-unit construction and decoding, to the visual data to extract time boundary information that they would lack otherwise. The resulting phonetic sub-units offer new perspectives for sign language analysis, phonetic modeling, and automatic recognition. We evaluate this approach via sign language recognition experiments on an extended Lemmas Corpus of Greek Sign Language, which results not only in improved performance compared to pure data-driven approaches, but also in meaningful phonetic sub-unit models that can be further exploited in interdisciplinary sign language analysis. © 2011 IEEE.	en
heal.journalName	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops	en
dc.identifier.doi	10.1109/CVPRW.2011.5981681	en