Thesis (Ph. D.)--University of Nevada, Reno, 2007. / "August, 2007." Includes bibliographical references (leaves 97-107). Library also has microfilm. Ann Arbor, Mich. : ProQuest Information and Learning Company, [2008]. 1 microfilm reel ; 35 mm. Online version available on the World Wide Web.

Thesis (B.Sc)--University of Hong Kong, 1993. / "A dissertation submitted in partial fulfilment of the requirements for the Bachelor of Science (Speech and Hearing Sciences), The University of Hong Kong, April, 30, 1993. Also available in print.

No description available.

動作 (sig) 是手語重要的音系參數之一。 但對於怎樣以音系形式來描述其特性，特別是怎樣把動作分類及賦予其相關的特徵，至今仍未達成一致的觀點。 為了填補這塊空白，此研究透過香港手語 (HKSL) 的語料，特別探討這些動作是否具有對比性、是否受規律支配、以及是否具組織結構。 基於對《香港手語詞典》(Tang 2007) 紀錄的1982個手語詞彙中1473個的觀察，我們留意到不同的動作種類、重複類型和它們同時出現的規律，並提出相關的動作分類和特徵。 在把動作視為一個具有內部結構的整體的前提下 (Brentari 1998)，此研究採用特徵構架 (feature geometry) 的框架 (Clements 1985, Sagey 1986, McCarthy 1988, Halle 1992) 分析動作特徵在結構樹下的不同層次。 我們又提出形式特徵 [重複] ([repeat]) 和 [返回] ([return]) 用來描述手語裏不同類型的“重複動作，它們以非重複、單向重複、雙向重複、局部動作重複、動作返回和顫動的形態出現。 此兩特徵都是動作類別非限定的發語方式，因為它們沒有被限定要出現在特定的動作類別。 雖然如此，它們在複合動作的分佈卻受某些規律支配，這令我們提出以複式領域的概念來解釋：一個外部領域 (DomainM) 包含所有動作類別，另一內部領域 (DomainS) 只包含可作為次動作的動作類別。 最後，本論文將提出把各動作類別組織成一個五層的特徵架構：(一) 動態特徵類 (MOVEMENT FEATURE / MF) 對 內在特徵類 (INHERENT FEATURE / IF)，(二) 離散類 (DISCRETE) 對 連續類 (CONTINUOUS)，(三) 位移類 (TRANSLOCATED) 對 駐留類 (STATIONARY)，(四) 路徑類 (PATH) 對 局部類 (LOCAL)，以及 (五) 手向類 (ORIENTATION) 對 開合類 (APERTURE)。 一個包含複合動作的手語可以分析為好幾個同步的動作類別 (即手語音系的基本單位)。 五個主要音類特徵 [±M]、[±D]、[±T]、[±P] 和 [±O] 被用來交叉分類以上的動作類別，及決定它們的音響層級 (sonority hierarchy)。 我們分析手語為根節點 (root node) 是根據手語同時利用次音段的複雜性 (即類似複音段) 和動態特性 (即類似曲拱音段) 的觀察結果。 / Movement (sig) is one of the major phonological parameters in sign phonology. However, there has been a lack of consensus on how to characterize it, in particular, how to organize movement classes and their associated features in a phonological representation. To fill this gap, this thesis attempts to examine whether movements are contrastive, constrained and structurally organized, based on 1473 lexical signs out of the 1982 signs documented in the HKSL dictionary (Tang 2007). The observations on movement types, repetitions, and their co-occurrence patterns motivate our proposal of new movement classes and features. Following the assumption that movement is a phonological category with an internal structure (Brentari 1998), this study adopts the feature geometry framework (Clements 1985, Sagey 1986, McCarthy 1988, Halle 1992) to analyze the relevant movement features and propose how they are organized in a hierarchical fashion. We also invoke the formal features [repeat] and [return] to capture the different realizations of “repetitions in signs, which may take the forms of non-repeated movement, unidirectional repetitions, bidirectional repetitions, repeated local movements, returning movements and trills. We propose that [repeat] and [return] are type-independent manner features because they are not restrictive to a specific movement type. However, the constrained distribution of these features in complex movements suggests a nested domain of occurrence: an outer domain (i.e. DomainM), which includes all movement classes and an inner domain (i.e. DomainS), which includes only a subset of movement classes associated with secondary movement. Finally, this thesis proposes a feature geometry with movement classes organized in a five-level hierarchy: (i) MOVEMENT FEATURE (MF) versus INHERENT FEATURE (IF) class, (ii) DISCRETE versus CONTINUOUS class, (iii) TRANSLOCATED versus STATIONARY class, (iv) PATH versus LOCAL class, and (v) ORIENTATION versus APERTURE class. A sign with complex movements can be analyzed as movement classes (i.e. the basic phonological units of signs) organized simultaneously. Five major class features [±M], [±D], [±T], [±P] and [±O] are proposed to cross-classify these movement classes and determine their sonority hierarchy. The reason why we adopt a sign-as-root-node analysis is due to the observation that signs exhibit both subsegmental complexity (i.e. complex-segment-like) and dynamicity (i.e. contour-segment-like) at the same time. / Detailed summary in vernacular field only. / Mak, Ka Leong. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2012. / Includes bibliographical references (leaves 287-300) and indexes. / Abstracts also in Chinese. / Thesis Committee --- p.i / Abstract of thesis entitled --- p.ii / Acknowledgement --- p.iv / Contents --- p.vii / List of figures --- p.xi / List of tables --- p.xvii / Notational conventions --- p.xxii / Chapter Chapter 1. --- Introduction --- p.1 / Chapter 1.1. --- Background --- p.1 / Chapter 1.2. --- Movement as a phonological category --- p.2 / Chapter 1.3. --- Research questions --- p.8 / Chapter 1.3.1. --- Are movements contrastive? --- p.8 / Chapter 1.3.2. --- Are movements rule-governed? --- p.10 / Chapter 1.3.3. --- Are movements structurally organized? --- p.11 / Chapter 1.4. --- Organization of this thesis --- p.14 / Chapter Chapter 2. --- Literature review --- p.17 / Chapter 2.1. --- Generative phonology: a review --- p.17 / Chapter 2.1.1. --- The Sound Pattern of English (SPE) --- p.18 / Chapter 2.1.2. --- Autosegmental phonology --- p.19 / Chapter 2.1.3. --- Feature geometry --- p.20 / Chapter 2.1.3.1. --- Basic premises --- p.21 / Chapter 2.1.3.2. --- The Articulator model --- p.24 / Chapter 2.1.3.3. --- Double domination --- p.28 / Chapter 2.1.3.4. --- Skeleton and major classes --- p.29 / Chapter 2.1.4. --- Nature of distinctive features --- p.30 / Chapter 2.1.4.1. --- Feature dynamicity --- p.30 / Chapter 2.1.4.2. --- Feature binarity --- p.31 / Chapter 2.2. --- Movement in sign phonology: a review --- p.34 / Chapter 2.2.1. --- Movement and hold as segments (MH model) --- p.35 / Chapter 2.2.2. --- Movement and location as segments (HT model) --- p.36 / Chapter 2.2.3. --- Movement with mora as handshape-bearing unit (Moraic model) --- p.37 / Chapter 2.2.4. --- A “movement-less approach (DP model) --- p.40 / Chapter 2.2.5. --- Movement as prosodic feature class node (Prosodic model) --- p.43 / Chapter 2.2.6. --- Repeated movement as single-segment (OneSeg model) --- p.48 / Chapter 2.2.7. --- Sign phonology models: a summary --- p.49 / Chapter 2.3. --- Representing movement in our model --- p.51 / Chapter Chapter 3. --- Contrastive movement types and features in HKSL --- p.55 / Chapter 3.1. --- Methodology --- p.55 / Chapter 3.2. --- Observations on the movement types in HKSL --- p.57 / Chapter 3.2.1. --- Simple and complex movements --- p.57 / Chapter 3.2.2. --- Distribution of basic movement types in HKSL --- p.58 / Chapter 3.2.3. --- Contrastive movement types --- p.59 / Chapter 3.3. --- Path movement --- p.62 / Chapter 3.3.1. --- Degrees of freedom: traveling motions --- p.64 / Chapter 3.3.2. --- Planes of articulation --- p.65 / Chapter 3.3.3. --- Orientation --- p.66 / Chapter 3.3.3.1. --- Problem: handpart-to-plane representation of orientation --- p.67 / Chapter 3.3.3.2. --- Solution: orientation contrast by handpart --- p.68 / Chapter 3.3.4. --- Direction and tracing --- p.70 / Chapter 3.3.4.1. --- Problem: how to specify tracing direction --- p.72 / Chapter 3.3.4.2. --- Solution: the primacy of setting in path --- p.73 / Chapter 3.3.5. --- Contrastive path directions --- p.79 / Chapter 3.3.6. --- Contrastive path shapes --- p.80 / Chapter 3.3.6.1. --- Spherical surfaces in the signing space --- p.82 / Chapter 3.3.6.2. --- Arc paths --- p.82 / Chapter 3.3.6.3. --- Circular paths --- p.83 / Chapter 3.4. --- Local movement --- p.85 / Chapter 3.4.1. --- Orientation change --- p.86 / Chapter 3.4.1.1. --- Degrees of freedom: rotating motions --- p.87 / Chapter 3.4.1.2. --- Contrastive orientation features --- p.88 / Chapter 3.4.2. --- Aperture change --- p.90 / Chapter 3.4.2.1. --- Degree of freedom: deformation --- p.90 / Chapter 3.4.2.2. --- Contrastive aperture features --- p.91 / Chapter 3.4.3. --- Path movement versus local movement --- p.94 / Chapter 3.4.4. --- Phonetic reduction, enhancement and implementation --- p.97 / Chapter 3.5. --- Setting change --- p.100 / Chapter 3.5.1. --- Path versus setting change --- p.102 / Chapter 3.5.2. --- Change of setting values --- p.104 / Chapter 3.5.3. --- Discrete orientation and aperture changes --- p.108 / Chapter 3.6. --- Repetitions, returning movements and trills --- p.110 / Chapter 3.6.1. --- Observations in HKSL --- p.113 / Chapter 3.6.2. --- Full repetitions --- p.116 / Chapter 3.6.3. --- Return --- p.117 / Chapter 3.6.4. --- Trills --- p.119 / Chapter 3.7. --- Summary: proposed movement features --- p.128 / Chapter Chapter 4. --- Feature organization of movement in HKSL --- p.129 / Chapter 4.1. --- Class nodes and features --- p.129 / Chapter 4.1.1. --- Basic assumptions --- p.130 / Chapter 4.1.2. --- Root node, IF and MF class nodes --- p.131 / Chapter 4.2. --- Co-occurrence patterns of different movement types --- p.132 / Chapter 4.2.1. --- Signs with no movement --- p.133 / Chapter 4.2.2. --- Co-occurrence pattern and movement type class nodes --- p.136 / Chapter 4.2.3. --- PATH-LOCAL distinction and class nodes --- p.138 / Chapter 4.3. --- Internal structures of PATH, ORI and APER class nodes --- p.139 / Chapter 4.3.1. --- SET and PATH class nodes --- p.140 / Chapter 4.3.2. --- ORI and APER class nodes --- p.145 / Chapter 4.3.3. --- Summary of PATH, ORI and APER class nodes --- p.149 / Chapter 4.4. --- Type-independent manner features --- p.150 / Chapter 4.4.1. --- Pattern of repetitions --- p.151 / Chapter 4.4.1.1. --- Constraints on repetitions --- p.152 / Chapter 4.4.1.2. --- Structural account for the constraints --- p.156 / Chapter 4.4.1.3. --- Lexical versus post-lexical constraints --- p.162 / Chapter 4.4.2. --- Exceptional movement characteristics --- p.166 / Chapter 4.4.2.1. --- Discrete change --- p.166 / Chapter 4.4.2.2. --- Temporal misalignment --- p.168 / Chapter 4.4.2.3. --- Revised constraints on repetitions --- p.169 / Chapter 4.4.3. --- Notion of domination --- p.174 / Chapter 4.4.3.1. --- Phonological domain of a feature --- p.175 / Chapter 4.4.3.2. --- Nested phonological domain --- p.177 / Chapter 4.5. --- Multiple projections of MF class node --- p.180 / Chapter 4.5.1. --- DISCRETE and CONTINUOUS class nodes --- p.181 / Chapter 4.5.2. --- TRANSLOC and STATIONARY class nodes --- p.187 / Chapter 4.5.3. --- Movement major classes --- p.196 / Chapter 4.5.4. --- Major classes and maximal signs --- p.203 / Chapter 4.6. --- Summary: proposed constraints represented in feature tree --- p.206 / Chapter Chapter 5. --- Conclusion and future research --- p.211 / Chapter 5.1. --- Answers to the research questions --- p.211 / Chapter 5.1.1. --- Movements are categorical and contrastive --- p.211 / Chapter 5.1.2. --- Movements are rule-governed and structurally organized --- p.216 / Chapter 5.1.3. --- Significance of the current study --- p.222 / Chapter 5.1.4. --- Limitations of the current study --- p.225 / Chapter 5.2. --- Future research --- p.226 / Chapter 5.2.1. --- Cross-linguistic evidence --- p.227 / Chapter 5.2.2. --- Empirical evidence --- p.227 / Chapter 5.2.3. --- Theory advancement --- p.228 / Chapter Appendix A. --- Segmental and syllable structures in sign language --- p.230 / Chapter A.1. --- In the search for segment in sign language --- p.230 / Chapter A.2. --- In the search for syllable in sign language --- p.232 / Chapter A.2.1. --- Syllable structure of sign --- p.233 / Chapter A.2.2. --- Classification of sign syllables --- p.235 / Chapter A.3. --- In the search for articulatory explanation --- p.242 / Chapter Appendix B. --- Phonology-phonetics interface --- p.245 / Chapter B.1. --- Levels of representation --- p.245 / Chapter B.2. --- Phonetic phenomena in sign language --- p.246 / Chapter B.2.1. --- Metathesis of settings --- p.253 / Chapter B.2.2. --- Insertion of epenthetic movement --- p.255 / Chapter B.2.3. --- Phonetic enhancement and reduction --- p.259 / Chapter B.2.4. --- Repetition implementation --- p.268 / Chapter B.3. --- Structure, phonology and phonetics --- p.275 / Bibliography --- p.287 / Index of illustrated signs --- p.301 / Index of discussed issues --- p.305 / Index of numbered examples --- p.308

Thesis (Ph. D.)--University of California, San Diego, 2003. / Vita. Includes bibliographical references (leaves 743-797).

Thesis (Ph. D.)--University of California, San Diego, 2006. / Title from first page of PDF file (viewed October 16, 2006). Available via ProQuest Digital Dissertations. Vita. Includes bibliographical references.

Doctor Educationis / Research has shown that five parameters are required to recognize any sign language gesture: hand shape, location, orientation and motion, as well as facial expressions. The South African Sign Language (SASL) research group at the University of the Western Cape has created systems to recognize Sign Language gestures using single parameters. Using a single parameter can cause ambiguities in the recognition of signs that are similarly signed resulting in a restriction of the possible vocabulary size. This research pioneers work at the group towards combining multiple parameters to achieve a larger recognition vocabulary set. The proposed methodology combines hand location and hand shape recognition into one combined recognition system. The system is shown to be able to recognize a very large vocabulary of 50 signs at a high average accuracy of 74.1%. This vocabulary size is much larger than existing SASL recognition systems, and achieves a higher accuracy than these systems in spite of the large vocabulary. It is also shown that the system is highly robust to variations in test subjects such as skin colour, gender and body dimension. Furthermore, the group pioneers research towards continuously recognizing signs from a video stream, whereas existing systems recognized a single sign at a time. To this end, a highly accurate continuous gesture segmentation strategy is proposed and shown to be able to accurately recognize sentences consisting of five isolated SASL gestures.

ABSTRACT Context: Communication is a primary human need and language is the medium for this. Most people have the ability to listen and speak and they use different languages like Swedish, Urdu and English etc. to communicate. Hearing impaired people use signs to communicate. Pakistan Sign Language (PSL) is the preferred language of the deaf in Pakistan. Currently, human PSL interpreters are required to facilitate communication between the deaf and hearing; they are not always available, which means that communication among the deaf and other people may be impaired or nonexistent. In this situation, a system with voice recognition as an input and PSL as an output will be highly helpful. Objectives: As part of this thesis, we explore challenges faced by deaf people in everyday life while interacting with unimpaired. We investigate state of art work done in this area. This study explores speech recognition and Machine translation techniques to devise a generic and automated system that converts English speech to PSL. A prototype of the proposed solution is developed and validated. Methods: Three step investigation is done as part of thesis work. First, to understand problem itself, interviews were conducted with the domain experts. Secondly, from literature review, it is investigated whether any similar or related work has already been done, state of the art technologies like Machine translation, speech recognition engines and Natural language processing etc. have been analyzed. Thirdly, prototype is developed whose validation data is obtained from domain experts and is validated by ourselves as well as from domain experts. Results: It is found that there is a big communication gap between deaf and unimpaired in Pakistan. This is mainly due to the lack of an automated system that can convert Audio speech to PSL and vice versa. After investigating state of the art work including solutions in other countries specific to their languages, it is found that no system exists that is generic and automated. We found that there is already work started for PSL to English Speech conversion but not the other way around. As part of this thesis, we discovered that a generic and automated system can be devised using speech recognition and Machine translation techniques. Conclusion: Deaf people in Pakistan lack a lot of opportunities mainly due to communication gap between deaf and unimpaired. We establish that there should be a generic and automated system that can convert English speech to PSL and vice versa. As part of this, we worked for such a system that can convert English speech to PSL. Moreover, Speech recognition, Machine translation and Natural language processing techniques can be core ingredients for such a generic and automated system. Using user centric approach, the prototype of the system is validated iteratively from domain experts. / This research has investigated a computer based solution to facilitate communication among deaf people and unimpaired. Investigation was performed using literature review and visits to institutes to gain a deeper knowledge about sign language and specifically how is it used in Pakistan context. Secondly, challenges faced by deaf people to interact with unimpaired are analyzed by interviews with domain experts (instructors of deaf institutes) and by directly observing deaf in everyday life situations. We conclude that deaf people rely on sign language for communication with unimpaired people. Deaf people in Pakistan use PSL for communication, English is taught as secondary language all over Pakistan in all educational institutes, deaf people are taught by instructors that not only need to know the domain expertise of the area that they are teaching like Math, History and Science etc. but they also need to know PSL very well in order to teach the deaf. It becomes very difficult for deaf institutes to get instructors that know both. Whenever deaf people need to communicate with unimpaired people in any situation, they either need to hire a translator or request the unimpaired people to write everything for them. Translators are very difficult to get all the time and they are very expensive as well. Moreover, using writing by unimpaired becomes very slow process and not all unimpaired people want to do this. We observed this phenomena ourselves as instructors of the institutes provided us the opportunity to work with deaf people to understand their feelings and challenges in everyday life. In this way, we used to go with deaf people in shopping malls, banks, post offices etc. and with their permission, we observed their interaction. We have concluded that sometimes their interaction with normal people becomes very slow and embarrassing. Based on above findings, we concluded that there is definitely a need for an automated system that can facilitate communication between deaf and unimpaired people. These factors lead to the subsequent objective of this research. The main objective of this thesis is to identify a generic and an automated system without any human intervention that converts English speech into PSL as a solution to bridge the communication gap between deaf and unimpaired. It is identified that existing work done related to this problem area doesn’t fulfill our objective. Current solutions are either very specific to a domain, e.g. post office or need human intervention i.e. not automatic. It is identified that none of the existing systems can be extended towards our desired solution. We explored state of the art techniques like Machine translation, Speech recognition and NLP. We have utilized these in our proposed solution. Prototype of the proposed solution is developed whose functional and non functional validation is performed. Since none of existing work exactly matches to our problem statement, therefore, we have not compared the validation of our prototype to any existing system. We have validated prototype with respect to our problem domain. Moreover, this is validated iteratively from the domain experts, i.e. experts of PSL and the English to PSL human translators. We found this user centric approach very useful to help better understand the problem at the ground level, keeping our work user focused and then realization of user satisfaction level throughout the process. This work has opened a new world of opportunities where deaf can communicate with others who do not have PSL knowledge. Having this system, if it is further developed from a prototype to a functioning system; deaf institutes will have wider scope of choosing best instructors for a given domain that may not have PSL expertise. Deaf people will have more opportunities to interact with other members of the society at every level as communication is the basic pillar for this. The automatic speech to sign language is an attractive prospect; the impending applications are exhilarating and worthwhile. In the field of Human Computer Interface (HCI) we hope that our thesis will be an important addition to the ongoing research. / Ahmed Abdul Haseeb & Asim ilyas, Contact no. 00923215126749 House No. 310, Street No. 4 Rawal town Islamabad, Pakistan Postal Code 44000

<p>This thesis presents an approach for automatically generating signing animations from a sign language notation. An avatar endowed with expressive gestures, as subtle as changes in facial expression, is used to render the sign language animations. SWML, an XML format of SignWriting is provided as input. It transcribes sign language gestures in a format compatible to virtual signing. Relevant features of sign language gestures are extracted from the SWML. These features are then converted to body animation pa- rameters, which are used to animate the avatar. Using key-frame animation techniques, intermediate key-frames approximate the expected sign language gestures. The avatar then renders the corresponding sign language gestures. These gestures are realistic and aesthetically acceptable and can be recognized and understood by Deaf people.</p>

<p>This thesis presents an approach for automatically generating signing animations from a sign language notation. An avatar endowed with expressive gestures, as subtle as changes in facial expression, is used to render the sign language animations. SWML, an XML format of SignWriting is provided as input. It transcribes sign language gestures in a format compatible to virtual signing. Relevant features of sign language gestures are extracted from the SWML. These features are then converted to body animation pa- rameters, which are used to animate the avatar. Using key-frame animation techniques, intermediate key-frames approximate the expected sign language gestures. The avatar then renders the corresponding sign language gestures. These gestures are realistic and aesthetically acceptable and can be recognized and understood by Deaf people.</p>