Gestos são ações que fazem parte da comunicação humana. Frequentemente, eles ocorrem junto com a fala e podem se manifestar por uma ação proposital, como o uso das mãos para explicar o formato de um objeto, ou como um padrão de comportamento, como coçar a cabeça ou ajeitar os óculos. Os gestos ajudam o locutor a construir sua fala e também ajudam o ouvinte a compreender a mensagem que está sendo transmitida. Pesquisadores de diversas áreas são interessados em entender como se dá a relação dos gestos com outros elementos do sistema linguístico, seja para suportar estudos das áreas da Linguística e da Psicolinguística, seja para melhorar a interação homem-máquina. Há diferentes linhas de estudo que exploram essa temática e entre elas está aquela que analisa os gestos a partir de fases: preparação, pré-stroke hold, stroke, pós-stroke hold, hold e retração. Assim, faz-se útil o desenvolvimento de sistemas capazes de automatizar a segmentação de um gesto em suas fases. Técnicas de aprendizado de máquina supervisionado já foram aplicadas a este problema e resultados promissores foram obtidos. Contudo, há uma dificuldade inerente à análise das fases do gesto, a qual se manifesta na alteração do contexto em que os gestos são executados. Embora existam algumas premissas básicas para definição do padrão de manifestação de cada fase do gesto, em contextos diferentes tais premissas podem sofrer variações que levariam a análise automática para um nível de alta complexidade. Este é o problema abordado neste trabalho, a qual estudou a variabilidade do padrão inerente à cada uma das fases do gesto, com apoio de aprendizado de máquina, quando a manifestação delas se dá a partir de um mesmo indivíduo, porém em diferentes contextos de produção do discurso. Os contextos de discurso considerados neste estudo são: contação de história, improvisação, descrição de cenas, entrevistas e aulas expositivas / Gestures are actions that make part of human communication. Commonly, gestures occur at the same time as the speech and they can manifest either through an intentional act, as using the hands to explain the format of an object, or as a pattern of behavior, as scratching the head or adjusting the glasses. Gestures help the speaker to build their speech and also help the audience to understand the message being communicated. Researchers from several areas are interested in understanding what the relationship of gestures with other elements of the linguistic system is like, whether in supporting studies in Linguistics or Psycho linguistics, or in improving the human-machine interaction. There are different lines of study that explore such a subject, and among them is the line that analyzes gestures according to their phases: preparation, pre-stroke hold, stroke, post-stroke hold, hold and retraction. Thus, the development of systems capable of automating the segmentation of gestures into their phases can be useful. Techniques that implement supervised machine learning have already been applied in this problem and promising results have been achieved. However, there is an inherent difficulty to the analysis of phases of gesture that is revealed when the context (in which the gestures are performed) changes. Although there are some elementary premises to set the pattern of expression of each gesture phase, such premises may vary and lead the automatic analysis to high levels of complexity. Such an issue is addressed in the work herein, whose purpose was to study the variability of the inherent pattern of each gesture phase, using machine learning techniques, when their execution is made by the same person, but in different contexts. The contexts of discourse considered in this study are: storytelling, improvisation, description of scenes, interviews and lectures

Gestos são ações que fazem parte da comunicação humana. Frequentemente, eles ocorrem junto com a fala e podem se manifestar por uma ação proposital, como o uso das mãos para explicar o formato de um objeto, ou como um padrão de comportamento, como coçar a cabeça ou ajeitar os óculos. Os gestos ajudam o locutor a construir sua fala e também ajudam o ouvinte a compreender a mensagem que está sendo transmitida. Pesquisadores de diversas áreas são interessados em entender como se dá a relação dos gestos com outros elementos do sistema linguístico, seja para suportar estudos das áreas da Linguística e da Psicolinguística, seja para melhorar a interação homem-máquina. Há diferentes linhas de estudo que exploram essa temática e entre elas está aquela que analisa os gestos a partir de fases: preparação, pré-stroke hold, stroke, pós-stroke hold, hold e retração. Assim, faz-se útil o desenvolvimento de sistemas capazes de automatizar a segmentação de um gesto em suas fases. Técnicas de aprendizado de máquina supervisionado já foram aplicadas a este problema e resultados promissores foram obtidos. Contudo, há uma dificuldade inerente à análise das fases do gesto, a qual se manifesta na alteração do contexto em que os gestos são executados. Embora existam algumas premissas básicas para definição do padrão de manifestação de cada fase do gesto, em contextos diferentes tais premissas podem sofrer variações que levariam a análise automática para um nível de alta complexidade. Este é o problema abordado neste trabalho, a qual estudou a variabilidade do padrão inerente à cada uma das fases do gesto, com apoio de aprendizado de máquina, quando a manifestação delas se dá a partir de um mesmo indivíduo, porém em diferentes contextos de produção do discurso. Os contextos de discurso considerados neste estudo são: contação de história, improvisação, descrição de cenas, entrevistas e aulas expositivas / Gestures are actions that make part of human communication. Commonly, gestures occur at the same time as the speech and they can manifest either through an intentional act, as using the hands to explain the format of an object, or as a pattern of behavior, as scratching the head or adjusting the glasses. Gestures help the speaker to build their speech and also help the audience to understand the message being communicated. Researchers from several areas are interested in understanding what the relationship of gestures with other elements of the linguistic system is like, whether in supporting studies in Linguistics or Psycho linguistics, or in improving the human-machine interaction. There are different lines of study that explore such a subject, and among them is the line that analyzes gestures according to their phases: preparation, pre-stroke hold, stroke, post-stroke hold, hold and retraction. Thus, the development of systems capable of automating the segmentation of gestures into their phases can be useful. Techniques that implement supervised machine learning have already been applied in this problem and promising results have been achieved. However, there is an inherent difficulty to the analysis of phases of gesture that is revealed when the context (in which the gestures are performed) changes. Although there are some elementary premises to set the pattern of expression of each gesture phase, such premises may vary and lead the automatic analysis to high levels of complexity. Such an issue is addressed in the work herein, whose purpose was to study the variability of the inherent pattern of each gesture phase, using machine learning techniques, when their execution is made by the same person, but in different contexts. The contexts of discourse considered in this study are: storytelling, improvisation, description of scenes, interviews and lectures

Summaries in Afrikaans and English / Die term deiksis is afgelei van die Griekse woord deiktikos wat 'wys na' betaken, en verwys na daardie uitdrukkings wat in 'n taal gebruik word om die belangrikste orientasiepunte in 'n gespreksituasie te verwoord. Aile deiktiese interpretasies kan net relatief tot 'n spesifieke verwysingspunt (deiktiese sentrum) gemaak word. Vyf deiktiese kategoriee word onderskei. Persoonsdeiksis hou verband met die deiktiese persona, m.a.w. die spreker en aangesprokeneen moontlik 'n derde persoon indian hy/sy/dit in die gespreksituasie teenwoordig is. Persoonsdeiksis word hoofsaaklik in Noord-Sotho se kongruensie-en pronominale sisteem gereflekteer. Sosiale deiksis verwys na daardie uitdrukkings wat die spreker se houding teenoor die aangesprokene of die derde persoon weergee. In Noord-Sotho word leksikale items met 'n sosiaal--deiktiese funksie aangetrefwat die spreker se bewondering, afkeer of respek teenoor die aangesprokene reflekteer, asook verwantskapstenne en aanspreekvonne. Alhoewel Noord-Sotho se pro nominate stelsel neutraal is ten opsigte van geslag, is daar ander maniere om taalkundig 'n onderskeid tussen die geslagte te maak. Plekdeiktiese uitdrukkings word gebruik om die Jigging van 'n objek relatief tot die deiktiese sentrum te beskryf. Die posisie van die gespreksgenote of hulle fisiese gestaltes kan hierdie deiktiese sentrum uitmaak. In Noord-Sothoword demonstratiewe, demonstratief-kopulatiewe, lokatiewe kopulatiewe,lokatiewe bywoorde en sekere werkwoorde vir hierdie doe I aangewend. Tyddeiksis word in Noord-Sotho hoofsaaklik deur middel van temporale bywoorde geleksikaliseer en deur middel van tydsvonne in die werkwoord gegrammatikaliseer. Die interpretasie van hierdie uitdrukkings is van die deiktiese sentrum (tyd wanneer die uiting gemaak is) afhanklik. Temporale bywoorde sowel as die tydsvonn van die werkwoord beskryf die tyd wanneer die handeling plaasvind. Hierdie vonne sal aandui of die handeling v66r koderingstyd plaasgevind het (verlede tyd), of dit na koderingstyd sal plaasvind (toe~omende tyd), en of die handeling met koderingstyd saamval (teenwoordige tyd). Diskoersdeiksis verwys na daardie uitdrukkings wat gebruik word om na dele van die diskoers, of na naamwoordelike antesedente waarvoor daar nie 'n referent in die buitetaalse werklikheid bestaan nie, te verwys. In Noord-Sothoword demonstratiewe, pronomina van die derde persoon, demonstratief-kopulatiewe, sekere bywoorde, identifiserende kopulatiewe, sekere kwalifikatiewe en sekere voegwoorde vir hierdie doel aangewend. / The term deixis is derived from a Greek word deiktikos which means 'point at' and it is used in grammar to refer to those expressions which describe the essential points of orientation in a speech situation. The interpretation of deictic expressions can only be made in relation to a specific reference point (the deictic centre). Five deictic categories are distinguished. Person deixis concerns the deictic persons, that is the speaker, the addressee and possibly a third person if he/she/it is present in the speech situation. Person deixis is mainly reflected in the concordia! and the pronominal system of Northern Sotho. Social deixis refers to those expressions which reflect the speaker's attitude towards the addressee or the third person. Such expressions include lexical items which reflect the speaker's admiration, dislike or respect towards the addressee, as well as kinship terms and vocatives. Although the pronominal system of Northern Sotho is neutral with regard to sex, there are other linguistic ways in which gender distinctions can be drawn. Place deictic expressions are used to identify the location of an object relative to the deictic centre. The location of the speech participants or their bodies may constitute this deictic centre. Demonstratives, demonstrative-copulatives, locational copulatives, locative adverbs and certain verbs are used for this purpose in Northern Sotho. Time deixis is mainly lexicalised by means of temporal adverbs and grammaticalised by means of tense morphemes in the Northern Sotho verb. The interpretation of these expressions depends on the deictic centre (time when the utterance is made). Time adverbs as well as the tenses describe the time of an event. These structures will indicate whether the action took place before coding time (past tense), whether it will take place after coding time (future tense), or whether it coincides with coding time (present tense). Discourse deixis pertains to those expressions which are used to refer to parts of the discourse, or to nominal antecedents of which the referent is not present in the extra-linguistic context of the utterance. Demonstratives, demonstrative copulatives, third person pronouns, certain adverbs, identifying copulatives, certain qualificatives and certain conjunctions are used for this purpose in Northern Sotho. / African Languages / D Litt. et Phil. (Afrikatale)

Analytic knowledge about the systematic variation in a language has an important place in the description of the language. Such knowledge is interesting e.g. in the language teaching domain, as a background for various types of linguistic studies, and in the development of more dynamic speech technology applications. In previous studies, the effects of single variables or relatively small groups of related variables on the pronunciation of words have been studied separately. The work described in this thesis takes a holistic perspective on pronunciation variation and focuses on a method for creating general descriptions of phone-level pronunciation in discourse context. The discourse context is defined by a large set of linguistic attributes ranging from high-level variables such as speaking style, down to the articulatory feature level. Models of phone-level pronunciation in the context of a discourse have been created for the central standard Swedish language variety. The models are represented in the form of decision trees, which are readable for both machines and humans. A data-driven approach was taken for the pronunciation modelling task, and the work involved the annotation of recorded speech with linguistic and related information. The decision tree models were induced from the annotation. An important part of the work on pronunciation modelling was also the development of a pronunciation lexicon for Swedish. In a cross-validation experiment, several sets of pronunciation models were created with access to different parts of the attributes in the annotation. The prediction accuracy of pronunciation models could be improved by 42.2% by making information from layers above the phoneme level accessible during model training. Optimal models were obtained when attributes from all layers of annotation were used. The goal for the models was to produce pronunciation representations representative for the language variety and not necessarily for the individual speakers, on whose speech the models were trained. In the cross-validation experiment, model-produced phone strings were compared to key phonetic transcripts of actual speech, and the phone error rate was defined as the share of discrepancies between the respective phone strings. Thus, the phone error rate is the sum of actual errors and discrepancies resulting from desired adaptations from a speaker-specific pronunciation to a pronunciation reflecting general traits of the language variety. The optimal models gave an average phone error rate of 8.2%. / QC 20100901

Summaries in Afrikaans and English / Die term deiksis is afgelei van die Griekse woord deiktikos wat 'wys na' betaken, en verwys na daardie uitdrukkings wat in 'n taal gebruik word om die belangrikste orientasiepunte in 'n gespreksituasie te verwoord. Aile deiktiese interpretasies kan net relatief tot 'n spesifieke verwysingspunt (deiktiese sentrum) gemaak word. Vyf deiktiese kategoriee word onderskei. Persoonsdeiksis hou verband met die deiktiese persona, m.a.w. die spreker en aangesprokeneen moontlik 'n derde persoon indian hy/sy/dit in die gespreksituasie teenwoordig is. Persoonsdeiksis word hoofsaaklik in Noord-Sotho se kongruensie-en pronominale sisteem gereflekteer. Sosiale deiksis verwys na daardie uitdrukkings wat die spreker se houding teenoor die aangesprokene of die derde persoon weergee. In Noord-Sotho word leksikale items met 'n sosiaal--deiktiese funksie aangetrefwat die spreker se bewondering, afkeer of respek teenoor die aangesprokene reflekteer, asook verwantskapstenne en aanspreekvonne. Alhoewel Noord-Sotho se pro nominate stelsel neutraal is ten opsigte van geslag, is daar ander maniere om taalkundig 'n onderskeid tussen die geslagte te maak. Plekdeiktiese uitdrukkings word gebruik om die Jigging van 'n objek relatief tot die deiktiese sentrum te beskryf. Die posisie van die gespreksgenote of hulle fisiese gestaltes kan hierdie deiktiese sentrum uitmaak. In Noord-Sothoword demonstratiewe, demonstratief-kopulatiewe, lokatiewe kopulatiewe,lokatiewe bywoorde en sekere werkwoorde vir hierdie doe I aangewend. Tyddeiksis word in Noord-Sotho hoofsaaklik deur middel van temporale bywoorde geleksikaliseer en deur middel van tydsvonne in die werkwoord gegrammatikaliseer. Die interpretasie van hierdie uitdrukkings is van die deiktiese sentrum (tyd wanneer die uiting gemaak is) afhanklik. Temporale bywoorde sowel as die tydsvonn van die werkwoord beskryf die tyd wanneer die handeling plaasvind. Hierdie vonne sal aandui of die handeling v66r koderingstyd plaasgevind het (verlede tyd), of dit na koderingstyd sal plaasvind (toe~omende tyd), en of die handeling met koderingstyd saamval (teenwoordige tyd). Diskoersdeiksis verwys na daardie uitdrukkings wat gebruik word om na dele van die diskoers, of na naamwoordelike antesedente waarvoor daar nie 'n referent in die buitetaalse werklikheid bestaan nie, te verwys. In Noord-Sothoword demonstratiewe, pronomina van die derde persoon, demonstratief-kopulatiewe, sekere bywoorde, identifiserende kopulatiewe, sekere kwalifikatiewe en sekere voegwoorde vir hierdie doel aangewend. / The term deixis is derived from a Greek word deiktikos which means 'point at' and it is used in grammar to refer to those expressions which describe the essential points of orientation in a speech situation. The interpretation of deictic expressions can only be made in relation to a specific reference point (the deictic centre). Five deictic categories are distinguished. Person deixis concerns the deictic persons, that is the speaker, the addressee and possibly a third person if he/she/it is present in the speech situation. Person deixis is mainly reflected in the concordia! and the pronominal system of Northern Sotho. Social deixis refers to those expressions which reflect the speaker's attitude towards the addressee or the third person. Such expressions include lexical items which reflect the speaker's admiration, dislike or respect towards the addressee, as well as kinship terms and vocatives. Although the pronominal system of Northern Sotho is neutral with regard to sex, there are other linguistic ways in which gender distinctions can be drawn. Place deictic expressions are used to identify the location of an object relative to the deictic centre. The location of the speech participants or their bodies may constitute this deictic centre. Demonstratives, demonstrative-copulatives, locational copulatives, locative adverbs and certain verbs are used for this purpose in Northern Sotho. Time deixis is mainly lexicalised by means of temporal adverbs and grammaticalised by means of tense morphemes in the Northern Sotho verb. The interpretation of these expressions depends on the deictic centre (time when the utterance is made). Time adverbs as well as the tenses describe the time of an event. These structures will indicate whether the action took place before coding time (past tense), whether it will take place after coding time (future tense), or whether it coincides with coding time (present tense). Discourse deixis pertains to those expressions which are used to refer to parts of the discourse, or to nominal antecedents of which the referent is not present in the extra-linguistic context of the utterance. Demonstratives, demonstrative copulatives, third person pronouns, certain adverbs, identifying copulatives, certain qualificatives and certain conjunctions are used for this purpose in Northern Sotho. / African Languages / D Litt. et Phil. (Afrikatale)