Using written language to probe speech recognition models. Speech recognition models fall into two principal classes, with fundamentally different processing architectures. Feedback models (e.g. TRACE, McClelland & Elman, 1986) allow lexical knowledge to exert top-down control over phonemic analysis. Feedforward models (e.g. Merge, Norris, McQueen & Cutler, 2000) assume that information flow is entirely bottom-up. Our project adopts an innovative approach to testing between these model classe ....Using written language to probe speech recognition models. Speech recognition models fall into two principal classes, with fundamentally different processing architectures. Feedback models (e.g. TRACE, McClelland & Elman, 1986) allow lexical knowledge to exert top-down control over phonemic analysis. Feedforward models (e.g. Merge, Norris, McQueen & Cutler, 2000) assume that information flow is entirely bottom-up. Our project adopts an innovative approach to testing between these model classes, by examining the influence of written-word knowledge on speech perception. To distinguish the models, contrasts must test different processing levels and examine strategy effects. TRACE favors broad effects with limited strategic influence; Merge favors lexical effects that are necessarily sensitive to strategic factorsRead moreRead less
Tonal language development in Mandarin and Cantonese-speaking children with cochlear implants. Cochlear implantation in children is expanding in countries where tonal languages are spoken, despite limited evidence of the effectiveness of implant use in these settings. This project will examine the impact of implant use on children's perception of tone, their production of speech and assesses how this affects functional communication.
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE100100211
Funder
Australian Research Council
Funding Amount
$650,000.00
Summary
The Big Australian Speech Corpus: An audio-visual speech corpus of Australian English. Contemporary speech science and technology are driven by the availability of large speech corpora. While audio databases exist for languages spoken in America, Europe and Japan, there is currently no large auditory-visual database of spoken language, and certainly not one for Australian English. Here we will establish the Big Australian Speech Corpus, which will support a speech science research and developmen ....The Big Australian Speech Corpus: An audio-visual speech corpus of Australian English. Contemporary speech science and technology are driven by the availability of large speech corpora. While audio databases exist for languages spoken in America, Europe and Japan, there is currently no large auditory-visual database of spoken language, and certainly not one for Australian English. Here we will establish the Big Australian Speech Corpus, which will support a speech science research and development using Australian English and facilitate the development of Australian speech technology applications from automatic speech recognition and text-to-speech synthesis used in taxi and other ordering services, to hearing prostheses and talking head aids for learning-impaired children, and a range of security and forensic applications.Read moreRead less
Learning to talk whitefella way. Many Indigenous children speak Aboriginal English or 'Kriol', which often sounds very different to Standard Australian English. Understanding the differences between these languages, and how 'Kriol' affects the learning of English, will help us to better assist Indigenous children to learn English and likely improve their educational outcomes.
Discovering the developmental trajectory of lexical stress production. In English words some syllables are more strongly stressed than others. Most children will learn to emphasise these syllables appropriately but some will not. This project will help to understand the normal development of this vital aspect of speech production and allow more effective assistance to those who experience difficulties.
Mobile Indonesians: social differentiation and digital literacies in the twenty first century. This is the first dedicated study of the social implications of mobile telephony's recent and rapid popularisation throughout the country. This project will study metropolitan, urban and rural users to understand how mobile phones create the new and unexpected social networks which will shape tomorrow's Indonesians.
Discovery Early Career Researcher Award - Grant ID: DE190100458
Funder
Australian Research Council
Funding Amount
$406,716.00
Summary
Understanding algorithmic distribution in the Australian media industry. This project examines how the use of algorithms to distribute content on social media platforms is affecting the Australian media sector. It will investigate how media professionals work with algorithms, what sort of media content is prioritised on these platforms and whether these algorithms affect content diversity and competition. This project will significantly advance our understanding of how social media platforms fun ....Understanding algorithmic distribution in the Australian media industry. This project examines how the use of algorithms to distribute content on social media platforms is affecting the Australian media sector. It will investigate how media professionals work with algorithms, what sort of media content is prioritised on these platforms and whether these algorithms affect content diversity and competition. This project will significantly advance our understanding of how social media platforms function as media distributors and the role of algorithmic systems within the workplace. Findings will inform current policy debates around the role of major social media platforms in a transforming media sector.Read moreRead less
Engaging with Social Media in Museums. This project will prototype the use of social media in museums to produce a new source of high-quality cultural information, and link regional, rural and international users with city-based institutions. It implements National Research Priority Frontier Technologies for Building and Transforming Australian Industries: promoting an innovation culture and economy and smart information use.
The Australian museum sector is undergoing a period of substantial c ....Engaging with Social Media in Museums. This project will prototype the use of social media in museums to produce a new source of high-quality cultural information, and link regional, rural and international users with city-based institutions. It implements National Research Priority Frontier Technologies for Building and Transforming Australian Industries: promoting an innovation culture and economy and smart information use.
The Australian museum sector is undergoing a period of substantial change in response to policy and technology initiatives, yet little formal collaboration exists between museums and researchers. This project brings some of the country's major museums together with the Smithsonian Institution, one of the world's foremost cultural institutions.Read moreRead less
Special Research Initiatives - Grant ID: SR0354576
Funder
Australian Research Council
Funding Amount
$30,000.00
Summary
Spatially Integrated Social Science Research in Australia. Rapid change across society has resulted in shifts to the scope of social science research including the emergence of space and place as an important concept. Across research fields the result has been that a range of innovative and unique techniques, methodologies and theories that are space based are now being developed. While research is progressing rapidly, it is undertaken in parallel by researchers who can not always collaborate. ....Spatially Integrated Social Science Research in Australia. Rapid change across society has resulted in shifts to the scope of social science research including the emergence of space and place as an important concept. Across research fields the result has been that a range of innovative and unique techniques, methodologies and theories that are space based are now being developed. While research is progressing rapidly, it is undertaken in parallel by researchers who can not always collaborate. Recognising these advances, this initiative focuses on harnessing Australia's capacity and potential in the use of spatially based methods and theories and brings researchers together in collaboration across a number of fields. Read moreRead less
ARC Research Network in Spatially Integrated Social Science. The ARC Research Network in Spatially Integrated Social Science (SISS) builds Australia's capacity and capability for innovative, collaborative, cross-disciplinary effort to investigate the impacts of change on the behaviour and well-being of people and the fortunes of places. SISS theories and research tools permit the integration of diverse and complex databases, the generation of new synthetic datasets, the incorporation of spatial ....ARC Research Network in Spatially Integrated Social Science. The ARC Research Network in Spatially Integrated Social Science (SISS) builds Australia's capacity and capability for innovative, collaborative, cross-disciplinary effort to investigate the impacts of change on the behaviour and well-being of people and the fortunes of places. SISS theories and research tools permit the integration of diverse and complex databases, the generation of new synthetic datasets, the incorporation of spatial concepts into statistical analysis and modelling, powerful visualisation of information, and the building spatial decision support systems, to provide an improved evidence base and better informed decision-making to address the significant challenges facing Australia's people and its places.Read moreRead less