Speech recognition adaptation for low resource populations. Automatic speech recognition is an essential attribute of mobile devices and consumer electronics. Unfortunately, as these systems are trained with adult speech, they perform poorly when used by children and people with speaking difficulties. The lack of available training speech from these groups makes developing models for them difficult. We will investigate efficient model adaptation methods that use minimal training data to adapt ex ....Speech recognition adaptation for low resource populations. Automatic speech recognition is an essential attribute of mobile devices and consumer electronics. Unfortunately, as these systems are trained with adult speech, they perform poorly when used by children and people with speaking difficulties. The lack of available training speech from these groups makes developing models for them difficult. We will investigate efficient model adaptation methods that use minimal training data to adapt existing adult speech recognition models for use with children and people with speaking difficulties. The intended outcomes will improve access to automatic speech recognition systems for Australians whose communication with speech-controlled environmental and educational devices is currently restricted.Read moreRead less
Two-way Auslan: Automatic Machine Translation of Australian Sign Language. This project aims to develop an automatic two-way machine-translation system between Auslan (Australian Sign Language) and English by researching and leveraging advanced computer vision and machine learning technology. The project expects to advance research in AI technology on topics including visual recognition, language processing and deep learning. This will boost Australia's national research capacity and global com ....Two-way Auslan: Automatic Machine Translation of Australian Sign Language. This project aims to develop an automatic two-way machine-translation system between Auslan (Australian Sign Language) and English by researching and leveraging advanced computer vision and machine learning technology. The project expects to advance research in AI technology on topics including visual recognition, language processing and deep learning. This will boost Australia's national research capacity and global competitiveness. Expected outcomes of this project will help to break the communication barriers between the Deaf and hearing population. This should provide significant benefits to Deaf communities through enhanced communication and improved quality-of-life, leading to a fair, more inclusive and resilient Australian society.Read moreRead less
Bridging the meaning gap: A computational approach to semantic variation. This project aims to create and validate a new class of large language models that capture and partially explain semantic variation between people. We will (1) measure nuanced differences in word meaning and linguistic experience across individuals; (2) develop computational models that incorporate this variation; and (3) evaluate the extent to which the models capture behavioural and cognitive differences related to polit ....Bridging the meaning gap: A computational approach to semantic variation. This project aims to create and validate a new class of large language models that capture and partially explain semantic variation between people. We will (1) measure nuanced differences in word meaning and linguistic experience across individuals; (2) develop computational models that incorporate this variation; and (3) evaluate the extent to which the models capture behavioural and cognitive differences related to political affiliation, gender, and culture. This will advance our understanding of the nature and origin of individual differences as well as improve the calibration of AI systems for under-represented groups. These advances will support eventual applied outcomes in health, domestic security, and resilience to misinformation. Read moreRead less
Beyond Speech: Towards better communication for children with hearing loss. Despite the benefits of early newborn hearing screening and early intervention programs for children with hearing loss, most still experience academic and social challenges at school. This is partly due to ongoing listening effort, leading to communicative breakdown. This project aims to identify the locus of the communicative challenges these children face during daily discourse interactions. The outcomes will identify ....Beyond Speech: Towards better communication for children with hearing loss. Despite the benefits of early newborn hearing screening and early intervention programs for children with hearing loss, most still experience academic and social challenges at school. This is partly due to ongoing listening effort, leading to communicative breakdown. This project aims to identify the locus of the communicative challenges these children face during daily discourse interactions. The outcomes will identify which levels of language are most compromised and will inform future interventions to reduce children’s listening effort. This will be undertaken by bringing together researchers in basic science with hearing service providers, parents and industry, providing an innovative model for solving multidisciplinary challenges.Read moreRead less
The perception/production link in child language. Children with hearing loss experience continuing language difficulties, with major knock-on effects on educational and social outcomes. This project aims to uncover the connected perception and production processes that underpin these language challenges for children with hearing loss, focussing on a speech patterns also found in younger normal-hearing toddlers, and using innovative technologies that can generalize to the clinical practice. The p ....The perception/production link in child language. Children with hearing loss experience continuing language difficulties, with major knock-on effects on educational and social outcomes. This project aims to uncover the connected perception and production processes that underpin these language challenges for children with hearing loss, focussing on a speech patterns also found in younger normal-hearing toddlers, and using innovative technologies that can generalize to the clinical practice. The project outcomes will significantly advance theories of child language development, and promise to inform more accurate and better-targeted intervention for children with hearing loss, providing social benefit by improving their listening and speaking skills.Read moreRead less
Automatic detection and modelling of acoustic markers of speech timing. This project aims to create new automatic sensing, analysis and assessment of cognitive, affective, mental and physical state from voice for mobile and computing devices. This project expects to generate new understanding of the effects of these states on detailed timing indicators of speech motor control, and new signal processing and machine learning methods that best exploit it. Expected outcomes from this project include ....Automatic detection and modelling of acoustic markers of speech timing. This project aims to create new automatic sensing, analysis and assessment of cognitive, affective, mental and physical state from voice for mobile and computing devices. This project expects to generate new understanding of the effects of these states on detailed timing indicators of speech motor control, and new signal processing and machine learning methods that best exploit it. Expected outcomes from this project include a new and accurate deep neural network framework for learning, analysing and detecting human states from speech automatically using articulatory timing markers. This should provide significant benefits, such as individually-tailored, frequent and low-cost automatic detection, monitoring and analytics for adverse states.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE220100783
Funder
Australian Research Council
Funding Amount
$409,781.00
Summary
Music and speech as a window into the predictive brain . Prediction is fundamental to daily life, and yet we know little about how this central process works in the brain. This research program aims to provide in-depth insight into predictive processing by investigating the precise, culturally relevant, and communicative domains of music and speech. The research expects to reveal cognitive and neural correlates of “what” will occur and “when” it will occur, while exploiting the musician brain as ....Music and speech as a window into the predictive brain . Prediction is fundamental to daily life, and yet we know little about how this central process works in the brain. This research program aims to provide in-depth insight into predictive processing by investigating the precise, culturally relevant, and communicative domains of music and speech. The research expects to reveal cognitive and neural correlates of “what” will occur and “when” it will occur, while exploiting the musician brain as a model for plasticity. Expected outcomes include a multi-dimensional model of prediction and its neural markers that will lay the foundation to investigate impaired predictive processing. This should substantially benefit health and education by providing perspectives for training and rehabilitation.Read moreRead less
Does word similarity across languages help or hinder bilingual speakers? This project aims to understand in more detail how bilinguals can accurately speak in both their languages. Speaking is a complex skill, particularly if you have two languages to choose from, which will be true for over half of Australia’s population by 2025. This project aims to investigate the factors that influence speech production in both monolinguals and bilinguals including those with language impairment, and develop ....Does word similarity across languages help or hinder bilingual speakers? This project aims to understand in more detail how bilinguals can accurately speak in both their languages. Speaking is a complex skill, particularly if you have two languages to choose from, which will be true for over half of Australia’s population by 2025. This project aims to investigate the factors that influence speech production in both monolinguals and bilinguals including those with language impairment, and develop a better bilingual theory. The benefit of this new theory will be to provide a clear basis for diagnosis and treatment for children in bilingual households who have problems learning to speak, and for bilingual people with language problems after a stroke or dementia.Read moreRead less
Origins of Phonology and Lexicon: Abstract representations before 6 months. Language is one of the most sophisticated human abilities, yet infants learn it easily. The current view is that the origins of language are abstract representations of consonants and vowels that start to form at 6-10 months. However, recent evidence shows that abstraction begins before 3 months, and that carer-infant conversations are vital to the process. This study involves tracking infants’ behavioural and brain deve ....Origins of Phonology and Lexicon: Abstract representations before 6 months. Language is one of the most sophisticated human abilities, yet infants learn it easily. The current view is that the origins of language are abstract representations of consonants and vowels that start to form at 6-10 months. However, recent evidence shows that abstraction begins before 3 months, and that carer-infant conversations are vital to the process. This study involves tracking infants’ behavioural and brain development from 1 to 18 months and analysing carer-infant speech, to determine how early abstraction supports vocabulary growth, how carer speech assists this process, and what early conditions predict language development, thus benefiting earlier identification of language delay, and saving significantly on later remediation.Read moreRead less