A5021197217- Assistive Technology in Communication and Mobility
- Shakespeare, Adaptation, and Literary Criticism
- Speech Recognition and Synthesis
- Voice and Speech Disorders
- Irish and British Studies
- Theater, Performance, and Music History
- Manufacturing Process and Optimization
- Speech and dialogue systems
- Scientific Computing and Data Management
- Natural Language Processing Techniques
- Family and Disability Support Research
- Phonetics and Phonology Research
- Text Readability and Simplification
- Folklore, Mythology, and Literature Studies
- scientometrics and bibliometrics research
- Dysphagia Assessment and Management
- Australian History and Society
- Topic Modeling
- Communication in Education and Healthcare
- Data Quality and Management
- BIM and Construction Integration
- Innovations in Medical Education
- Research Data Management Practices
- Amyotrophic Lateral Sclerosis Research
- Theatre and Performance Studies
University College London
2019-2024
Motor Neurone Disease Association
2022-2024
Google (United States)
2022-2024
Cheshire West and Chester
2019
Bial (Portugal)
2018
Royal Holloway University of London
2016
Public Library of Science
2006-2015
Film Independent
2015
Emory University
2013
The University of Texas at Austin
2013
Users of augmentative and alternative communication (AAC) devices sometimes find it difficult to communicate in real time with others due the takes compose messages. AI technologies such as large language models (LLMs) provide an opportunity support AAC users by improving quality variety text suggestions. However, these may fundamentally change how interact transition from typing their own phrases prompting selecting AI-generated phrases. We conducted a study which 12 tested live suggestions...
Automatic Speech Recognition (ASR) systems, despite significant advances in recent years, still have much room for improvement particularly the recognition of disordered speech. Even so, erroneous transcripts from ASR models can help people with speech be better understood, especially if transcription doesn't significantly change intended meaning. Evaluating efficacy this use case requires a methodology measuring impact errors on meaning and comprehensibility. Human evaluation is gold...
Motor neuron disease (MND) is a fatal, progressive neurodegenerative that causes weakening and wasting of limb, bulbar, thoracic abdominal muscles. Clear evidence-based guidance on how psychological distress should be managed in people living with MND (plwMND) lacking. Acceptance Commitment Therapy (ACT) form therapy may particularly suitable for this population. However, to the authors' knowledge, no study date has evaluated ACT plwMND. Consequently, primary aim uncontrolled feasibility was...
This study examines the effectiveness of automatic speech recognition (ASR) for individuals with disorders, addressing gap in performance between read and conversational ASR. We analyze factors influencing this disparity effect mode-specific training on ASR accuracy.
We developed dysarthric speech intelligibility classifiers on 551,176 disordered samples contributed by a diverse set of 468 speakers, with range self-reported speaking disorders and rated for their overall five-point scale. trained three models following different deep learning approaches evaluated them ~ 94K utterances from 100 speakers. further found the to generalize well (without training) TORGO database[1] (100% accuracy), UASpeech[2] (0.93 correlation), ALS-TDI PMP[3] (0.81 AUC)...
Ben Jonson and Theatre is an investigation celebration of Jonson's plays from the point view theatre practitioner as well teacher. Reflecting increasing interest in wider field Renaissance drama, this book bridges theory/practice divide by debating how drama operates performance. includes: * discussions with between practitioners essays on staging edited transcripts interviews contemporary The volume includes contributions Joan Littlewood, Sam Mendes, John Nettles, Simon Russell Beale...
More than 80% of people living with MND (plwMND) develop difficulties their speech, affecting communication, self-identity and quality life. Most plwMND eventually use an augmentative alternative communication device (AAC) to communicate. Some AAC devices provide a synthesized voice for however these voices are often viewed as impersonal factor in acceptance. Voice banking creates approximation the person's own that can be used is argued go some way preserve identity when natural lost, but...
Word Error Rate (WER) is the primary metric used to assess automatic speech recognition (ASR) model quality.It has been shown that ASR models tend have much higher WER on speakers with impairments than typical English speakers.It hard determine if can be useful at such high error rates.This study investigates use of BERTScore, an evaluation for text generation, provide a more informative measure quality and usefulness.Both BERTScore were compared prediction errors manually annotated by...
Although personalized automatic speech recognition (ASR) models have recently been improved to recognize even severely impaired speech, model performance may degrade over time for persons with degenerating speech. The aims of this study were (1) analyze the change ASR in individuals degrading and (2) explore mitigation strategies optimize throughout disease progression. Speech was recorded by four due amyotrophic lateral sclerosis (ALS). Word error rates (WER) across recording sessions...
Amyotrophic lateral sclerosis (ALS) is a progressive, ultimately fatal disease causing progressive muscular weakness. Most people living with ALS (plwALS) experience dysarthria, eventually becoming unable to communicate using natural speech. Many wish use speech for as long possible. Personalized automated recognition (ASR) model technology, such Google's Project Relate, argued better recognize supporting maintenance of understanding through real-time captioning. The objectives this study...
Interest in and use of article-level metrics (ALMs) has grown rapidly amongst the research community, by researchers, publishers, funders, institutions. As this happens, it is critical to ensure secure reliable data that trustworthy can be used all. Two case studies are presented, which illustrate different approaches establishing ALM integrity.
Accelerating communication for users with severe motor and speech impairments, in particular eye-gaze-based augmentative alternative (AAC) device users, is a longstanding area of research. However, observation such users' over extended durations has been limited. This case study presents the real-world experience developing field-testing tool observing curating gaze typing-based an eye-gaze AAC user amyotrophic lateral sclerosis (ALS). With intent to observe develop technology accelerate...
While the impact of article citations has been examined for decades, “altmetrics” movement exploded in past year. Altmetrics tracks activity on Social Web and looks at research outputs besides articles. Publishers scientific have enabled altmetrics their articles, open source applications are available platforms to display research, subscription models created that provide altmetrics. In future, will be used help identify broader quickly high-impact research.
In Ghana people who struggle to articulate speech as a result of different conditions experience barriers in interacting with others due difficulties being understood. Automatic recognition software can be used help listeners understand communication difficulties. However, studies have not looked at the practical feasibility these technologies beyond Global North. We present novel user study examining introduction one such technology, Google Project Relate, Ghana. This freely available...
Project Euphonia, a Google initiative, is dedicated to improving automatic speech recognition (ASR) of disordered speech. A central objective the project create large, high-quality, and diverse corpus. This report describes project's latest advancements in data collection annotation methodologies, such as expanding speaker diversity database, adding human-reviewed transcript corrections audio quality tags 350K (of 1.2M total) recordings, amassing comprehensive set metadata (including more...
Project Euphonia, a Google initiative, is dedicated to improving automatic speech recognition (ASR) of disordered speech. A central objective the project create large, high-quality, and diverse corpus. This report describes project's latest advancements in data collection annotation methodologies, such as expanding speaker diversity database, adding human-reviewed transcript corrections audio quality tags 350K (of 1.2M total) recordings, amassing comprehensive set metadata (including more...
Abstract Background: Motor neuron disease (MND) is a progressive, fatal, neurodegenerative condition that affects motor neurons in the brain and spinal cord, resulting loss of ability to move, speak, swallow breathe. Acceptance commitment therapy (ACT) an acceptance-based behavioural may be particularly beneficial for people living with MND (plwMND). This qualitative study aimed explore plwMND’s experiences receiving adapted ACT, tailored their specific needs, therapists’ delivering it....