• Digital Humanities and Cultural Heritage
• Publications close
• Research data close
• Conference object close
• Edinburgh Research Archive close

Presentation given at the Open Repositories Conference 2016, Trinity College, Dublin. The end-to-end workflow for annotations via image tagging at the University of Edinburgh.

This case study focuses on a project using a crowdsourced metadata ‘game’ to develop collections, and shows that once you have a process in place, it is not too creating engagement with your collections. The public can help solve your problem, provided you have coffee and somewhere for them to sit.

In recent years the University of Edinburgh [UoE] has seen change, mergers, external partnerships and innovation at the heart of its growth and activity. Collections at UoE were not immune from these changes and have pioneered projects that both support and highlight unique educational cultures. Technology and the dissemination of collections has not only engendered positive relationships with academics but has created wider opportunities for the use of collections in teaching, learning and research. This momentum and an established commitment to the interoperability of data and standards presented an opportunity to look for a global solution to collections management within the converged, cross disciplinary environment. This included harnessing expertise in the University with systems development for large European projects and wider project management. This session will explore how UoE became the first European contributor to the collections management tool Archives Space. Snapshots of a converged culture and how 'archives' have benefited from this (including how 'techies' and 'archivists' worked together). An upbeat finale will look at what the team at the UoE achieved and are excited about for the future.

This paper describes a speaker discrimination experiment in which native English listeners were presented with natural and synthetic speech stimuli in English and were asked to judge whether they thought the sentences were spoken by the same person or not. The natural speech consisted of recordings of Finnish speakers speaking English. The synthetic stimuli were created using adaptation data from the same Finnish speakers. Two average voice models were compared: one trained on Finnish-accented English and the other on American-accented English. The experiments illustrate that listeners perform well at speaker discrimination when the stimuli are both natural or both synthetic, but when the speech types are crossed performance drops significantly. We also found that the type of accent in the average voice model had no effect on the listeners' speaker discrimination performance.

The difference between native speakers’ and non-native speakers’ naturalness judgements of synthetic speech is investigated. Similar/difference judgements are analysed via a multidimensional scaling analysis and compared to Mean opinion scores. It is shown that although the two groups generally behave in a similar manner the variance of non-native speaker judgements is generally higher. While both groups of subject can clearly distinguish natural speech from the best synthetic examples, the groups’ responses to different artefacts present in the synthetic speech can vary. Index Terms: speech synthesis, evaluation, non-native

We analyse the contribution of higher-level elements of the linguistic specification of a data-driven speech synthesiser to the naturalness of the synthetic speech which it generates. The system is trained using various subsets of the full feature-set, in which features relating to syntactic category, intonational phrase boundary, pitch accent and boundary tones are selectively removed. Utterances synthesised by the different configurations of the system are then compared in a subjective evaluation of their naturalness. The work presented forms background analysis for an ongoing set of experiments in performing text-to-speech (TTS) conversion based on shallow features: features that can be trivially extracted from text. By building a range of systems, each assuming the availability of a different level of linguistic annotation, we obtain benchmarks for our on-going work. Index Terms: Statistical parametric speech synthesis, HMMbased speech synthesis, HTS, ToBI, prosody

This paper examines the role of gender in the relationship between labour market status and preferences for job security. We hypothesize that the insider/ outsider theory of employment and unemployment suffers from a gender bias. It neither takes the possibility of family-related labour market transitions nor the role of the household situation (division of labour, presence of children, dual-earner households etc.) into account. We adapt the insider/ outsider theory of employment and unemployment by incorporating the, on average, higher number of labour market transitions experienced by women into the model using interaction effects and by conceptualising the household situation as mobility and responsibility effects. Contrary to our expectations, we find no significant effect of gender on preferences for job security, neither in interaction with labour market status nor as an independent effect. In contrast, we observe that individuals living together with their partners and main contributors to the household income consider job security to be particularly important.

In the EMIME project, we are developing a mobile device that performs personalized speech-to-speech translation such that a user's spoken input in one language is used to produce spoken output in another language, while continuing to sound like the user's voice. We integrate two techniques, unsupervised adaptation for HMM-based TTS using a word-based large-vocabulary continuous speech recognizer and cross-lingual speaker adaptation for HMM-based TTS, into a single architecture. Thus, an unsupervised cross-lingual speaker adaptation system can be developed. Listening tests show very promising results, demonstrating that adapted voices sound similar to the target speaker and that differences between supervised and unsupervised cross-lingual speaker adaptation are small. 14-19 March 2010Dallas, TX, USA