Evaluating parts-of-speech taggers for use in a text-to-scene conversion system

This paper presents parts-of-speech tagging as a first step towards an autonomous text-to-scene conversion system. It categorizes some freely available taggers, according to the techniques used by each in order to automatically identify word-classes. In addition, the performance of each identified tagger is verified experimentally. The SUSANNE corpus is used for testing and reveals the complexity of working with different tagsets, resulting in substantially lower accuracies in our tests than in those reported by the developers of each tagger. The taggers are then grouped to form a voting system to attempt to raise accuracies, but in no cases do the combined results improve upon the individual accuracies. Additionally a new metric, agreement, is tentatively proposed as an indication of confidence in the output of a group of taggers where such output cannot be validated.

Constraint-based conversion of fiction text to a time-based graphical representation

This paper presents a method for converting unrestricted fiction text into a time-based graphical form. Key concepts extracted from the text are used to formulate constraints describing the interaction of entities in a scene. The solution of these constraints over their respective time intervals provides the trajectories for these entities in a graphical representation.

Three types of entity are extracted from fiction books to describe the scene, namely Avatars, Areas and Objects. We present a novel method for modeling the temporal aspect of a fiction story using multiple time-line representations after which the information extracted regarding entities and time-lines is used to formulate constraints. A constraint solving technique based on interval arithmetic is used to ensure that the behaviour of the entities satisfies the constraints over multiple universally quantified time intervals. This approach is demonstrated by finding solutions to multiple time-based constraints, and represents a new contribution to the field of Text-to-Scene conversion. An example of the automatically produced graphical output is provided in support of our constraint-based conversion scheme.

Medical free-text to concept mapping as an information retrieval problem

Concept mapping involves determining relevant concepts from a free-text input, where concepts are defined in an external reference ontology. This is an important process that underpins many applications for clinical information reporting, derivation of phenotypic descriptions, and a number of state-of-the-art medical information retrieval methods. Concept mapping can be cast into an information retrieval (IR) problem: free-text mentions are treated as queries and concepts from a reference ontology as the documents to be indexed and retrieved. This paper presents an empirical investigation applying general-purpose IR techniques for concept mapping in the medical domain. A dataset used for evaluating medical information extraction is adapted to measure the effectiveness of the considered IR approaches. Standard IR approaches used here are contrasted with the effectiveness of two established benchmark methods specifically developed for medical concept mapping. The empirical findings show that the IR approaches are comparable with one benchmark method but well below the best benchmark.

New Method for Delexicalization and its Application to Prosodic Tagging for Text-to-Speech Synthesis

This paper describes a new flexible delexicalization method based on glottal excited parametric speech synthesis scheme. The system utilizes inverse filtered glottal flow and all-pole modelling of the vocal tract. The method provides a possibil- ity to retain and manipulate all relevant prosodic features of any kind of speech. Most importantly, the features include voice quality, which has not been properly modeled in earlier delex- icalization methods. The functionality of the new method was tested in a prosodic tagging experiment aimed at providing word prominence data for a text-to-speech synthesis system. The ex- periment confirmed the usefulness of the method and further corroborated earlier evidence that linguistic factors influence the perception of prosodic prominence.

Continuity Metric for Unit Selection based Text-to-Speech Synthesis

A new method based on unit continuity metric (UCM) is proposed for optimal unit selection in text-to-speech (TTS) synthesis. UCM employs two features, namely, pitch continuity metric and spectral continuity metric. The methods have been implemented and tested on our test bed called MILE-TTS and it is available as web demo. After verification by a self selection test, the algorithms are evaluated on 8 paragraphs each for Kannada and Tamil by native users of the languages. Mean-opinion-score (MOS) shows that naturalness and comprehension are better with UCM based algorithm than the non-UCM based ones. The naturalness of the TTS output is further enhanced by a new rule based algorithm for pause prediction for Tamil language. The pauses between the words are predicted based on parts-of-speech information obtained from the input text.

Research bed for unit selection based text to speech synthesis

The paper describes a modular, unit selection based TTS framework, which can be used as a research bed for developing TTS in any new language, as well as studying the effect of changing any parameter during synthesis. Using this framework, TTS has been developed for Tamil. Synthesis database consists of 1027 phonetically rich prerecorded sentences. This framework has already been tested for Kannada. Our TTS synthesizes intelligible and acceptably natural speech, as supported by high mean opinion scores. The framework is further optimized to suit embedded applications like mobiles and PDAs. We compressed the synthesis speech database with standard speech compression algorithms used in commercial GSM phones and evaluated the quality of the resultant synthesized sentences. Even with a highly compressed database, the synthesized output is perceptually close to that with uncompressed database. Through experiments, we explored the ambiguities in human perception when listening to Tamil phones and syllables uttered in isolation,thus proposing to exploit the misperception to substitute for missing phone contexts in the database. Listening experiments have been conducted on sentences synthesized by deliberately replacing phones with their confused ones.

Expressive visual text-to-speech using active appearance models

This paper presents a complete system for expressive visual text-to-speech (VTTS), which is capable of producing expressive output, in the form of a 'talking head', given an input text and a set of continuous expression weights. The face is modeled using an active appearance model (AAM), and several extensions are proposed which make it more applicable to the task of VTTS. The model allows for normalization with respect to both pose and blink state which significantly reduces artifacts in the resulting synthesized sequences. We demonstrate quantitative improvements in terms of reconstruction error over a million frames, as well as in large-scale user studies, comparing the output of different systems. © 2013 IEEE.

An overview of the ILSP unit selection text-to-speech synthesis system

This paper presents an overview of the Text-to-Speech synthesis system developed at the Institute for Language and Speech Processing (ILSP). It focuses on the key issues regarding the design of the system components. The system currently fully supports three languages (Greek, English, Bulgarian) and is designed in such a way to be as language and speaker independent as possible. Also, experimental results are presented which show that the system produces high quality synthetic speech in terms of naturalness and intelligibility. The system was recently ranked among the first three systems worldwide in terms of achieved quality for the English language, at the international Blizzard Challenge 2013 workshop. © 2014 Springer International Publishing.

Andrew Marvell's Latin Poetry: From Text to Context (356pp.)

David Norbrook, Review of English Studies 56 (Sept. 2005), 675-6.
‘We have waited a long time for a study of Marvell’s Latin poetry; fortunately, Estelle Haan’s monograph generously makes good the loss ... One of her most intriguing suggestions … is that Marvell may have presented paired poems like ‘Ros’ and ‘On a Drop of Dew’, and the poems to the obligingly named Dr Witty, to his student Maria Fairfax as his own patterns for the pedagogical practice of double translation. Perhaps the most original parts of the book, however, move beyond the familiar canon to cover the generic range of the Latin verse. Haan offers a very full contextualization of the early Horatian Ode to Charles I in seventeenth-century exercises in parodia. In a rewarding reading of the poem to Dr Ingelo she shows how Marvell deploys the language of Ovid’s Tristia to present Sweden as a place of shivering exile, only to subvert this model with a neo-Virgilian celebration of Christina as a virtuous, city-building Dido. She draws extensively on historical as well as literary sources to offer very detailed contextualizations of the poem to Maniban and ‘Scaevola Scotto-Britannus’... This monograph opens up many new ways into the Latin verse, not least because it is rounded off with new texts and prose translations of the Latin poems. These make a substantial contribution in their own right. They are the best and most accurate translations to date (those in Smith’s edition having some lapses); they avoid poeticisms but bring out the structure of the poems' wordplay very clearly. This book brings us a lot closer to seeing Marvell whole.'

Automatic syllabification for danish text-to-speech systems

In this paper, a rule-based automatic syllabifier for Danish is described using the Maximal Onset Principle. Prior success rates of rule-based methods applied to Portuguese and Catalan syllabification modules were on the basis of this work. The system was implemented and tested using a very small set of rules. The results gave rise to 96.9% and 98.7% of word accuracy rate, contrary to our initial expectations, being Danish a language with a complex syllabic structure and thus difficult to be rule-driven. Comparison with data-driven syllabification system using artificial neural networks showed a higher accuracy rate of the former system.

Using Ancillary Text to Index Web-based Multimedia Objects

PériCulture est le nom d'un projet de recherche à l'Université de Montréal qui fait partie d'un projet plus vaste basé à l'Université de Sherbrooke. Ce dernier visait à former un réseau de recherche pour la gestion du contenu culturel numérique canadien. L'objectif général de la recherche de PériCulture était d'étudier les méthodes d'indexation de contenus culturels non textuels sur le Web, plus spécifiquement des images. Les résultats de la recherche présentés ici s'appuient sur des travaux précédents en indexation d'images et en indexation automatique (de texte), par l'étude des propriétés du texte associé à des images dans un environnement réseau. Le but était de comprendre la façon dont le texte associé à des images sur des pages Web (appelé péritexte) peut être exploité pour indexer les images correspondantes. Nous avons étudié cette question dans le contexte de pages Web sélectionnées, c'est à dire : des pages de contenu culturel canadien contenant des objets multimédia auxquels était associé du texte (plus que simplement les noms de fichiers et les légendes) et qui étaient bilingues (anglais et français). Nous avons identifié les mots-clés utiles à l'indexation situés à proximité de l'objet décrit. Les termes d'indexation potentiels ont été identifiés dans diverses balises HTML et dans le texte intégral (chacun étant considéré comme une source différente de péritexte). Notre étude a révélé qu'un grand nombre de termes d'indexation utiles sont disponibles dans le péritexte de nombreux sites Web ayant un contenu culturel, et ce péritexte de différentes sources a une utilité variable dans la recherche d’information. Nos résultats suggèrent que ces termes peuvent être exploités de différentes manières dans les systèmes de recherche d’information pour améliorer les résultats de recherche.