A computational model of prosody for Yorùbá text-to-speech synthesis

This work examines prosody modelling for the Standard Yorùbá (SY) language in the context of computer text-to-speech synthesis applications. The thesis of this research is that it is possible to develop a practical prosody model by using appropriate computational tools and techniques which combines acoustic data with an encoding of the phonological and phonetic knowledge provided by experts. Our prosody model is conceptualised around a modular holistic framework. The framework is implemented using the Relational Tree (R-Tree) techniques (Ehrich and Foith, 1976). R-Tree is a sophisticated data structure that provides a multi-dimensional description of a waveform. A Skeletal Tree (S-Tree) is first generated using algorithms based on the tone phonological rules of SY. Subsequent steps update the S-Tree by computing the numerical values of the prosody dimensions. To implement the intonation dimension, fuzzy control rules where developed based on data from native speakers of Yorùbá. The Classification And Regression Tree (CART) and the Fuzzy Decision Tree (FDT) techniques were tested in modelling the duration dimension. The FDT was selected based on its better performance. An important feature of our R-Tree framework is its flexibility in that it facilitates the independent implementation of the different dimensions of prosody, i.e. duration and intonation, using different techniques and their subsequent integration. Our approach provides us with a flexible and extendible model that can also be used to implement, study and explain the theory behind aspects of the phenomena observed in speech prosody.

A modular holistic approach to prosody modelling for Standard Yorùbá speech synthesis

This paper presents a novel prosody model in the context of computer text-to-speech synthesis applications for tone languages. We have demonstrated its applicability using the Standard Yorùbá (SY) language. Our approach is motivated by the theory that abstract and realised forms of various prosody dimensions should be modelled within a modular and unified framework [Coleman, J.S., 1994. Polysyllabic words in the YorkTalk synthesis system. In: Keating, P.A. (Ed.), Phonological Structure and Forms: Papers in Laboratory Phonology III, Cambridge University Press, Cambridge, pp. 293–324]. We have implemented this framework using the Relational Tree (R-Tree) technique. R-Tree is a sophisticated data structure for representing a multi-dimensional waveform in the form of a tree. The underlying assumption of this research is that it is possible to develop a practical prosody model by using appropriate computational tools and techniques which combine acoustic data with an encoding of the phonological and phonetic knowledge provided by experts. To implement the intonation dimension, fuzzy logic based rules were developed using speech data from native speakers of Yorùbá. The Fuzzy Decision Tree (FDT) and the Classification and Regression Tree (CART) techniques were tested in modelling the duration dimension. For practical reasons, we have selected the FDT for implementing the duration dimension of our prosody model. To establish the effectiveness of our prosody model, we have also developed a Stem-ML prosody model for SY. We have performed both quantitative and qualitative evaluations on our implemented prosody models. The results suggest that, although the R-Tree model does not predict the numerical speech prosody data as accurately as the Stem-ML model, it produces synthetic speech prosody with better intelligibility and naturalness. The R-Tree model is particularly suitable for speech prosody modelling for languages with limited language resources and expertise, e.g. African languages. Furthermore, the R-Tree model is easy to implement, interpret and analyse.

Comparing sentence-level features for authorship analysis in Portuguese

In this paper we compare the robustness of several types of stylistic markers to help discriminate authorship at sentence level. We train a SVM-based classifier using each set of features separately and perform sentence-level authorship analysis over corpus of editorials published in a Portuguese quality newspaper. Results show that features based on POS information, punctuation and word / sentence length contribute to a more robust sentence-level authorship analysis. © Springer-Verlag Berlin Heidelberg 2010.

Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN

Different types of sentences express sentiment in very different ways. Traditional sentence-level sentiment classification research focuses on one-technique-fits-all solution or only centers on one special type of sentences. In this paper, we propose a divide-and-conquer approach which first classifies sentences into different types, then performs sentiment analysis separately on sentences from each type. Specifically, we find that sentences tend to be more complex if they contain more sentiment targets. Thus, we propose to first apply a neural network based sequence model to classify opinionated sentences into three types according to the number of targets appeared in a sentence. Each group of sentences is then fed into a one-dimensional convolutional neural network separately for sentiment classification. Our approach has been evaluated on four sentiment classification datasets and compared with a wide range of baselines. Experimental results show that: (1) sentence type classification can improve the performance of sentence-level sentiment analysis; (2) the proposed approach achieves state-of-the-art results on several benchmarking datasets.

Word order in Yiddish narrative discourse

Based on data from spoken narrative discourse in Yiddish, this paper analyses two structures common in Yiddish narrations: The placement of the finite verb in the first position of a declarative sentence, and topicalization.Like German, Yiddish word order is generally centered around a verb-second rule. However, both Yiddish and spoken German show configurations of word order that go against the rule, where the finite verb occupies the first position of the utterance. From a functional-pragmatic point of view, these structures can be said to serve special purposes in the interaction between speaker and listener, sometimes in particular discourse types.Differences and similarities in word order between Yiddish and German enable us to comment on the relationship between these two closely related languages.

Contribution à un bilan méthodologique de la syntaxe de l'émergence diachronique du sujet obligatoire en français::e paramètre du sujet nul et le statut des clitiques

As any language French transformed over time. The evolution of French is marked by many phenomena at all organization levels. For syntax, these phenomena include from the medieval State to current state the assertive sentence of second verb schema change (where the verb should be preceded by a constituent, XVY) to SVO (where it is the subject that precedes the verb) and the passage of the optional expression required expression of the subject. The mandatory presence of the subject in current French is all the more remarkable that it distinguishes it from most other major contemporary romance languages that require explicit subject. This last group includes catalan, Spanish, Italian literary, some occitans, Portuguese, Romanian, and Sardinian, dialects French hugging with the florentin franco-provençal, some other occitans dialects Mediterranean Italian dialects and the ladin following Vanelli, Renzi and Beninca (1985/1985).

Effects of differences in fundamental frequency on across-formant grouping in speech perception

In an isolated syllable, a formant will tend to be segregated perceptually if its fundamental frequency (F0) differs from that of the other formants. This study explored whether similar results are found for sentences, and specifically whether differences in F0 (?F0) also influence across-formant grouping in circumstances where the exclusion or inclusion of the manipulated formant critically determines speech intelligibility. Three-formant (F1 + F2 + F3) analogues of almost continuously voiced natural sentences were synthesized using a monotonous glottal source (F0 = 150 Hz). Perceptual organization was probed by presenting stimuli dichotically (F1 + F2C + F3; F2), where F2C is a competitor for F2 that listeners must resist to optimize recognition. Competitors were created using time-reversed frequency and amplitude contours of F2, and F0 was manipulated (?F0 = ±8, ±2, or 0 semitones relative to the other formants). Adding F2C typically reduced intelligibility, and this reduction was greatest when ?F0 = 0. There was an additional effect of absolute F0 for F2C, such that competitor efficacy was greater for higher F0s. However, competitor efficacy was not due to energetic masking of F3 by F2C. The results are consistent with the proposal that a grouping “primitive” based on common F0 influences the fusion and segregation of concurrent formants in sentence perception.

Speaking and pronunciation

We take as our starting point the notion of spoken language in use, drawing on insights from discourse analysis which makes it clear that language is used to negotiate and achieve meaning in social contexts and so cannot be divorced from those contexts. This perspective tasks us beyond a purely psycholinguistic model of speech where underlying mental processes are highlighted (e.g. Levelt, 1989). The perspective also takes us beyond the focus on the sentence, which has traditionally been the unit of analysis in much grammatical analysis and language teaching.

An investigation into formal and functional characteristics of qualifications in legislative writing and its application to English for academic legal purposes.

The present investigation is based on a linguistic analysis of the 'Housing Act 1980' and attempts to examine the role of qualifications in the structuring of the legislative statement. The introductory chapter isolates legislative writing as a "sub-variety “of legal language and provides an overview of the controversies surrounding the way it is written and the problems it poses to its readers. Chapter two emphasizes the limitations of the available work on the description of language-varieties for the analysis of legislative writing and outlines the approach adopted for the present analysis. This chapter also gives some idea of the information-structuring of legislative provisions and establishes qualification as a key element in their textualisation. The next three chapters offer a detailed account of the ten major qualification-types identified in the corpus, concentrating on the surface form they take, the features of legislative statements they textualize and the syntactic positions to which they are generally assigned in the statement of legislative provisions. The emerging hypotheses in these chapters have often been verified through a specialist reaction from a Parliamentary Counsel, largely responsible for the writing of the ‘Housing Act 1980’• The findings suggest useful correlations between a number of qualificational initiators and the various aspects of the legislative statement. They also reveal that many of these qualifications typically occur in those clause-medial syntactic positions which are sparingly used in other specialist discourse, thus creating syntactic discontinuity in the legislative sentence. Such syntactic discontinuities, on the evidence from psycholinguistic experiments reported in chapter six, create special problems in the processing and comprehension of legislative statements. The final chapter converts the main linguistic findings into a series of pedagogical generalizations, offers indications of how this may be applied in EALP situations and concludes with other considerations of possible applications.

Organizational and textual structuring of radio news discourse in English and Arabic.

The present work studies the overall structuring of radio news discourse via investigating three metatextual/interactive functions: (1) Discourse Organizing Elements (DOEs), (2) Attribution and (3) Sentential and Nominal Background Information (SBI & NBI). An extended corpus of about 73,000 words from BBC and Radio Damascus news is used to study DOEs and a restricted corpus of 38,000 words for Attribution and S & NBI. A situational approach is adopted to assess the influence of factors such as medium and audience on these functions and their frequence. It is found that: (1) DOEs are organizational and their frequency is determined by length of text; (2) Attribution Function in accordance with the editor's strategy and its frequency is audience sensitive; and (3) BI provides background information and is determined by audience and news topics. Secondly, the salient grammatical elements in DOEs are discourse deictic demonstratives, address pronouns and nouns referring to `the news'. Attribution is realized in reporting/reported clauses, and BI in a sentence, a clause or a nominal group. Thirdly, DOEs establish a hierarchy of (1) news, (2) summary/expansion and (3) item: including topic introduction and details. While Attribution is generally, and SBI solely, a function of detailing, NBI and proper names are generally a function of summary and topic introduction. Being primarily addressed to audience and referring metatextually, the functions investigated support Sinclair's interactive and autonomous planes of discourse. They also shed light on the part(s) of the linguistic system which realize the metatextual/interactive function. Strictly, `discourse structure' inevitably involves a rank-scale; but news discourse also shows a convention of item `listing'. Hence only within the boundary of variety (ultimately interpreted across language and in its situation) can textual functions and discourse structure be studied. Finally, interlingual variety study provides invaluable insights into a level of translation that goes beyond matching grammatical systems or situational factors, an interpretive level which has to be described in linguistic analysis of translation data.

Environmental and nature conservation : a facet study of concern for the quality of the natural environment

A multi-variate descriptive model of environmental and nature conservation attitudes and values is proposed and empirically supported. A mapping sentence is developed out of analysis of data from a series of Repertory Grid interviews addressing conservation employees' attitudes towards their profession's activities. The research is carried out within the meta-theoretical framework of Facet Theory. A mapping sentence is developed consisting of 9 facets. From the mapping sentence 3 questionnaires were constructed viewing the selective orientations towards environmental concern. A mapping sentence and facet model is developed for each study. Once the internal structure of this model had been established using Similarity Structure Analysis, the elements of the facets are subjected to Partial Order Scalogram Analysis with base coordinates. A questionnaire was statistically analysed to assess the relationship between facet elements and 4 measures of attitudes towards, and involvement with, conservation. This enabled the comparison of the relative strengths of attitudes associated with each facet element and each measure of conservation attitude. In general, the relationship between the social value of conservation and involvement pledges to conservation were monotonic; perceived importance of a conservation issue appearing predictive of personal involvement. Furthermore, the elements of the life area and scale facets were differentially related to attitude measures. The multi-variate descriptive model of environmental conservation values and attitudes is discussed in relation to its implications for psychological research into environmental concern and for environmental and nature conservation.

The discourse of biology lectures : aspects of its mode and text structure

The present thesis investigates mode related aspects in biology lecture discourse and attempts to identify the position of this variety along the spontaneous spoken versus planned written language continuum. Nine lectures (of 43,000 words) consisting of three sets of three lectures each, given by the three lecturers at Aston University, make up the corpus. The indeterminacy of the results obtained from the investigation of grammatical complexity as measured in subordination motivates the need to take the analysis beyond sentence level to the study of mode related aspects in the use of sentence-initial connectives, sub-topic shifting and paraphrase. It is found that biology lecture discourse combines features typical of speech and writing at sentence as well as discourse level: thus, subordination is more used than co-ordination, but one degree complexity sentence is favoured; some sentence initial connectives are only found in uses typical of spoken language but sub-topic shift signalling (generally introduced by a connective) typical of planned written language is a major feature of the lectures; syntactic and lexical revision and repetition, interrupted structures are found in the sub-topic shift signalling utterance and paraphrase, but the text is also amenable to analysis into sentence like units. On the other hand, it is also found that: (1) while there are some differences in the use of a given feature, inter-speaker variation is on the whole not significant; (2) mode related aspects are often motivated by the didactic function of the variety; and (3) the structuring of the text follows a sequencing whose boundaries are marked by sub-topic shifting and the summary paraphrase. This study enables us to draw four theoretical conclusions: (1) mode related aspects cannot be approached as a simple dichotomy since a combination of aspects of both speech and writing are found in a given feature. It is necessary to go to the level of textual features to identify mode related aspects; (2) homogeneity is dominant in this sample of lectures which suggests that there is a high level of standardization in this variety; (3) the didactic function of the variety is manifested in some mode related aspects; (4) the features studied play a role in the structuring of the text.

Comparing German and British political culture through values : and analysis of the values of health care reform

This research sets out to compare the values in British and German political discourse, especially the discourse of social policy, and to analyse their relationship to political culture through an analysis of the values of health care reform. The work proceeds from the hypothesis that the known differences in political culture between the two countries will be reflected in the values of political discourse, and takes a comparison of two major recent legislative debates on health care reform as a case study. The starting point in the first chapter is a brief comparative survey of the post-war political cultures of the two countries, including a brief account of the historical background to their development and an overview of explanatory theoretical models. From this are developed the expected contrasts in values in accordance with the hypothesis. The second chapter explains the basis for selecting the corpus texts and the contextual information which needs to be recorded to make a comparative analysis, including the context and content of the reform proposals which comprise the case study. It examines any contextual factors which may need to be taken into account in the analysis. The third and fourth chapters explain the analytical method, which is centred on the use of definition-based taxonomies of value items and value appeal methods to identify, on a sentence-by-sentence basis, the value items in the corpus texts and the methods used to make appeals to those value items. The third chapter is concerned with the classification and analysis of values, the fourth with the classification and analysis of value appeal methods. The fifth chapter will present and explain the results of the analysis, and the sixth will summarize the conclusions and make suggestions for further research.

Contradiction in universal and particular reasoning

A wide range of essential reasoning tasks rely on contradiction identification, a cornerstone of human rationality, communication and debate founded on the inversion of the logical operators "Every" and "Some." A high-density electroencephalographic (EEG) study was performed in 11 normal young adults. The cerebral network involved in the identification of contradiction included the orbito-frontal and anterior-cingulate cortices and the temporo-polar cortices. The event-related dynamic of this network showed an early negative deflection lasting 500 ms after sentence presentation. This was followed by a positive deflection lasting 1.5 s, which was different for the two logical operators. A lesser degree of network activation (either in neuron number or their level of phase locking or both) occurred while processing statements with "Some," suggesting that this was a relatively simpler scenario with one example to be figured out, instead of the many examples or the absence of a counterexample searched for while processing statements with "Every." A self-generated reward system seemed to resonate the recruited circuitry when the contradictory task is successfully completed.