VCCA2024 – Program Highlights
The scientific program of VCCA2024 will comprise interactive keynotes, featured and invited talks with scientific contributions and special sessions and workshops to highlight the wide range of world-class research and hot topics in computational audiology. Below are a selection of program highlights: keynotes, featured talks, special sessions & workshops and panel discussions. For the full program, click here.
Keynote and Featured Talks
Keynote speakers: | Topic and Bio |
 Dr. Manohar Bance | In his keynote, Professor Manohar Bance will explore the question “Could we make cochlear implants work better?” Cochlear implants are not getting any better over the last couple of decades. A large part of the problem is at the electrode-electrolyte interface. Our work examines the factors that prevent better focusing of electrical fields, the impact of different types of stimulus parameters on electrical field spread, the impact of electrode position on electrical fields, and how we can use measurements to inform models. We also discuss potential future therapies that might have some impact. Manohar is the inaugural Professor of Otology and Skull Base Surgery at the University of Cambridge and Honorary Consultant at the Cambridge University Hospitals Trust (Addenbrookes), appointed in 2017. Prior to his arrival in Cambridge, he was Professor and Head of the Division of Otolaryngology-Head and Neck Surgery at Dalhousie University in Canada, and Director of the EAR Lab there. |
 Deniz Başkent, PhD | Deniz is interested in all aspects of hearing, hearing loss, hearing aids and cochlear implants, and speech perception. Deniz’s current projects focus on children with hearing loss, voice and emotion perception, speech-in-speech perception, listening effort, and audiological diagnostic tests and rehabilitation approaches, such as music training and use of humanoid robots. In her talk she will discuss “New directions for diagnostic and rehabilitation tools”. Deniz will introduce research from the dB SPL Lab on new approaches to fully characterize hearing abilities and potential ways to improve them, in adults and children with atypical hearing and hearing devices. Some of these approaches use automatic speech recognition, robots, and music training. It is promised to be an informative and fun talk. |
 Lars Bramsløw, PhD | Lars has 30 years of extensive experience in acoustics, hearing science and hearing aid research and development, including employment at House Ear Institute in Los Angeles, Eriksholm and Oticon headquarters in Smørum, Denmark. He is currently working on improved fitting of hearing aids for the individual and the application of deep learning algorithms in hearing health care. His talk will be called “State of the art and future developments in hearing aid technology”. He will discuss the potential benefits and challenges in future hearing aid technology, including application of artificial intelligence. |
 Melanie Ferguson, PhD | Melanie Ferguson is Associate Professor in Brain and Hearing at Curtin University in Australia, and is a clinically-qualified audiologist. Her translational research interests are remote technologies and new service delivery models, listening and cognition including dementia, and outcome measures for adults with hearing loss. She has led research teams at the Ear Science Institute Australia in Perth, National Acoustic Laboratories, Sydney, and the NIHR Nottingham Biomedical Research Centre, UK. She has had leadership roles in UK Audiology and UK hearing healthcare policy-making. Her talk is titled “From nice-to-have to must-have: the essential role of co-design and participatory approaches in digital hearing healthcare”. |
Featured talks: | Topic and Bio |
 Professor Andrew Hugill | Professor Andrew Hugill will be giving a talk on “Aural Diversity: a general introduction”. Andrew is a composer, musicologist and computer scientist. He is a Principal Fellow of the HEA and a National Teacher Fellow. He has published many books and articles on topics ranging from digital music to pataphysics. He is the founder of the Aural Diversity Project http://auraldiversity.org and has led many conferences and concerts, workshops and media activities on that topic. He is the co-editor of the book Aural Diversity, published in 2022. His work often draws on his lived experience of invisible disabilities: autism, balance disorder and severe hearing loss. In this talk, he introduces the concept of Aural Diversity and discusses the scope of the field. Aural Diversity has become an increasingly influential idea in recent years across a range of disciplines including audiology and music, but also architecture and design, engineering and technology, computing and AI, and even literature and history. It starts from a premise that everybody hears differently and observes that current standards are inadequate to account for the many variations in hearing. Andrew himself has severe unbalanced hearing loss, tinnitus and diplacusis thanks to Meniere’s Disease, and is also autistic, so brings a unique perspective to bear. He presents the work of the Aural Diversity project auraldiversity.org, which includes a network funded by the AHRC, a doctoral college funded by the Leverhulme Trust, a series of concerts, workshops, seminars and events, and a collection of partnerships with organisations such as GNResound, Arup, DEFRA and the Welsh Government. |
 Anthea Bott, PhD | Anthea Bott will give a talk on “Optimizing manufacturing of custom hearing aids”. Anthea manages the R&D Insights and Machine Learning team at GN Hearing. Her team are responsible for managing and visualizing large tabular datasets on products and for developing and deploying cloud-based machine learning algorithms. She holds a master’s degree and PhD in Audiology from The University of Queensland, Australia. |
 Ariane Laplante-Lévesque, PhD World Health Organization Regional Office for Europe and Linköping University | Ariane Laplante-Lévesque will give a talk on “Improving access to hearing assistive technology: needs and best practices”. Ariane is a clinical audiologist from Canada with a PhD in Audiology and a Master’s of Public Health. She has thrived in applied research roles within the public, university, medical device industry, and inter-governmental sectors. Research interests include hearing rehabilitation interventions and their outcomes, the innovation of new eHealth approaches, and the application of scientific evidence to inform health policies. |
 Malcolm Slaney, PhD Stanford University | Malcolm will give a talk on “Bayesian Models of Speech Understanding for a Clinical Population”. Malcolm Slaney is an expert on machine learning and auditory modeling at Stanford University. His co-author, Dr. Matt Fitzgerald, oversees the Audiology departments of both Stanford Hospital and the Lucille Packard Children’s Hospital. |
 Professor Harvey Dillon Macquarie University | Harvey Dillon is a Professor in the Department of Linguistics at Macquarie University. He will give a talk on the causes of deficits in sentence understanding in noise, as revealed by an analysis of nearly 2000 clinical applications of the Listening in Spatialized Noise Sentences Test (LiSN-S). His research interests at Macquarie centre on auditory processing disorders in children. The questions that need answering are: 1. How can we determine how much of the listening difficulty experienced by a child is caused by deficits in each of auditory processing, speech sound identification, cognition, and language deficits? 2. Within each of these broad areas, but particularly within the auditory processing area, what is the nature of the specific underlying defict(s)? 3. How can deficits in auditory processing be remediated, and what else changes as a result? |
 Emma Holmes, PhD University College London (UCL), UK | Dr Emma Holmes will be giving a talk on “Directing selective attention in noisy environments is affected by hearing loss across the lifespan”. She is a Lecturer in Speech and Hearing Sciences at UCL. She studied Experimental Psychology at the University of Oxford and completed her PhD at the University of York under the supervision of Quentin Summerfield. She then worked as a postdoctoral fellow – first, at the Brain and Mind Institute (University of Western Ontario, Canada) with Ingrid Johnsrude, then at the Wellcome Centre for Human Neuroimaging (University College London) with Tim Griffiths and Karl Friston. She joined the Department of Speech Hearing and Phonetic Sciences at UCL as a Lecturer in 2021. |
 Siobhán Brennan, PhD University of Manchester and Sheffield Teaching Hospitals | Dr. Siobhán Brennan will be giving a talk on “The Audiology Learning Disabilities and Autism Project (ALDAP)”. She is currently an Audiology Lecturer at Manchester Centre for Audiology and Deafness, University of Manchester UK and a Lead Clinical Scientist at the Regional Department of Neurotology, Sheffield Teaching Hospitals UK. Siobhán has enjoyed a varied career specialising in auditory electrophysiology and Audiological care for individuals with intellectual impairment. In addition to clinical, research and educational roles, she has chaired groups focused on improving practice including the Hearing and Learning Disabilities special interest group and the British Society of Audiology Electrophysiology Special Interest Group. She is a member of the European Federation of Audiology Societies Working Group on Audiology and Intellectual Disability and the British Society of Audiology Cognition and Hearing Special Interest Group. |
 George Tilston Manchester Biomedical Research Centre, UK
| George Tilston will be presenting a talk on ‘Curating routinely collected hearing-health data to facilitate the equitable re-use of NHS data for translational research using the OMOP framework’. George is a Data Manager at the University of Manchester, based in the Centre for Health Informatics. As part of the Manchester Biomedical Research Centre (BRC), he helps researchers to gain access to valuable health data from various sources. One of George’s key roles is working as a Research Data Engineer (RDE) for the Greater Manchester (GM) Secure Data Environment (SDE), helping researchers to access health datasets and perform analysis in a secure setting. George also led the ethics application for the research aspects of the GM SDE, and is involved in other national data sharing initiatives such as the NIHR Health Informatics Collaborative, where data is combined across multiple hospitals. |
 Mareike Buhl, PhD Center for Research and Innovation in Human Audiology, Institut de l’Audition, Institut Pasteur, Paris, France | Mareike Buhl is a hearing researcher with the research interest of combining the fields of audiology, artificial intelligence, and data science – towards improving audiological patient care by exploiting knowledge from data. She is currently working as a PostDoc in the Hearing Institute in Paris. In her PhD thesis in Oldenburg, Mareike used her background in Physics with specialization in hearing research to establish abstract hearing loss parameters for comparing audiological databases. Mareike and Charlotte will be giving a talk on “Big data and data standards in audiology ” to precede the panel discussion they are chairing. |
 Charlotte Vercammen, PhD Sonova AG, Research & Development, Stäfa, Switzerland Manchester Centre for Audiology and Deafness, School of Health Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK Department of Neurosciences, Research Group Experimental Oto-Rhino-Laryngology, KU Leuven, University of Leuven, Belgium | Charlotte Vercammen is a research scientist at Sonova AG, an honorary lecturer at the Manchester Centre for Audiology and Deafness, and visiting professor at the Research Group of Experimental ORL in Leuven, Belgium. With a background in speech language pathology, audiology, and neurosciences, her current research interests focus on leveraging clinical data for the development of new algorithms and tools that could support more holistic hearing care. Charlotte and Mareike will be giving a talk on “Big data and data standards in audiology ” to precede the panel discussion they are chairing.
|
Special sessions / workshops
AAS and CAN Collaborative Workshop on Peer Review, Thursday June 20th, 2024
The American Auditory Society, the Editorial Board of Ear and Hearing, and the Computational Audiology Network have collaborated to offer an exciting virtual workshop for anyone interested in learning or updating their knowledge and skills for peer review of manuscripts. We have a group of highly experienced leaders who will provide the workshop and lead discussion breakouts. A free, three-hour interactive training session through Wolters Kluwer is highly recommended to prepare for the discussion (see link to the free basic online reviewer course).
Further details and the Workshop program are found here.
Open-source auditory models of normal-hearing and hearing-impaired processing (Fotios Drakopoulos and Alejandro Osses), Thursday June 20th, 2024
How do we process and perceive sound, and how does hearing change with age and noise exposure? At VCCA 2024, Fotios Drakopoulos and Alejandro Osses will demonstrate how existing computational models and recent machine-learning approaches can help us simulate auditory processing for normal-hearing and hearing-impaired listeners. We will compare a number of openly accessible auditory models on Python and MATLAB, that range from functional approximations of auditory perception to more complex descriptions of the physiological properties of the auditory system. We will discuss the widespread uptake of auditory models, and how they can be used to develop optimal sound-processing strategies that can serve the large population of people with hearing loss.
The following GitHub repository includes the MATLAB and Python demos that we will run during the workshop, installation instructions for each demo, as well as an extensive list of open-source auditory models and toolboxes: https://github.com/fotisdr/open_source_auditory_models
The attendees of the workshop are instructed to download the GitHub repository files beforehand, and also run any installation requirements (if provided) from the corresponding README file of the demo they wish to attend (MATLAB or Python folder of the repository).
Big data and data standards in audiology (Mareike Buhl and Charlotte Vercammen), Friday June 21st, 2024
Large data repositories provide a lot of potential for audiological diagnostics and the recommendation of hearing devices. To date, a large variety of data is collected in clinical as well as research settings, including studies with large numbers of patients. These data are typically collected in local databases, exhibiting different data structure, choice of tests, or varying data quality. If these data were analyzed together, knowledge about many patients worldwide could be exploited to obtain a representative overview of existing patient patterns; clinical data could be linked to data from population-based studies or health insurance databases; and targeted artificial intelligence (AI) methods could reveal new insights, for example estimating distinct patient profiles that show common combinations of test outcomes, satisfaction with hearing care, hearing aid benefit, or suggesting additional tests for those patients whose hearing deficits are not yet characterized in sufficient detail.
For exchanging data across institutions, or combining data from different data sources for analysis, the definition of data standards is crucial. A recently started community initiative (in the context of a European Federation of Audiological Societies (EFAS) working group) is based on the openEHR approach, which aims to achieve interoperability between databases by separating information and knowledge, through so-called archetypes and templates.
This session aims to assess the state-of-the-art of data standards available in audiology, and to discuss its potential, challenges, and required steps towards successful standardization. In the featured talk, we will introduce the openEHR approach, and discuss input from the VCCA community (collected by a survey conducted before). In the second part, we will have a panel discussion with experts offering their perspectives from audiology, data science/artificial intelligence, and database infrastructure such as electronic health records.
Please fill in the survey linked here to inform this session. Mareike and Charlotte would like to collect insights that will be presented and discussed in this special session. The target audience is anyone interested in (computational) audiology. The chairs are aiming to collect as many different perspectives as possible! Participating in the survey will take you 10-15 minutes.
Wiki Hearing (Hector Gabriel), Thursday June 20th, 2024
During the Wiki Hearing Workshop, participants will get the chance to learn the basics of Wikipedia editing, make substantive changes to Wikipedia articles and Wikidata items within content on hearing, sound, acoustics, audio, signal processing, environmental noise and related topics. More info can be found here.
How to share software and models via GitHub or other platforms (Gerardo Roa Dabike), Thursday June 20th, 2024
Nowadays, collaboration lies at the heart of innovation. GitHub has emerged as a cornerstone platform for developers, providing a robust infrastructure for version control, collaboration, and community engagement. GitHub offers a centralized hub for storing, managing, and sharing code repositories. Facilitates collaboration among teams, open-source contributions, and community-driven development. With features like pull requests, issue tracking, and automated workflows, GitHub streamlines the development process, fostering transparency, accountability, and productivity.
Join us for this online workshop designed to equip you with the essential skills for sharing code and collaborating efficiently using GitHub. Whether you’re a beginner taking your first steps in version control or an experienced developer seeking to enhance your proficiency, this workshop will demystify the GitHub workflow and empower you to contribute confidently to projects of any scale.
The workshop documentation is available here.
Panel sessions
Big data and data standards in audiology (Mareike Buhl and Charlotte Vercammen), Friday June 21st, 2024
Within their special session, and after their featured talk, Mareike and Charlotte will be chairing a panel discussion on big data and data standards in audiology.
Can we treat hearing loss better by considering the benefit of seeing a talker? (Chair: Chris Sumner), Thursday 20th June, 2024
It is well known that seeing the face of a talker boosts speech perception in noise. This boost is particularly important for people with a hearing impairment, and influences the real-world value of hearing aids and cochlear implants. Yet, this is not taken account in any systematic way when treating hearing problems. This session on audiovisual speech perception will ask our panel whether they think it is possible to improve treatment for hearing problems by considering the value people get from seeing the talker. Could this lead to more effective treatment for the individual? If so, how might it change treatment? What are the fundamental barriers to doing this? What research, clinical or basic, is needed to remove these barriers?
What people with and without hearing loss want from music (Chair: Alinka Greasley), Thursday 20th June, 2024
Musical engagement, whether listening or performing, is highly prevalent in everyday life and plays a key role in health and wellbeing. Music is a pleasurable activity that can enhance mood, regulate emotions, help with activities and bring back memories. These functions tend to be similar despite individual variation in preference for musical genres and characteristics. For those with hearing loss, who may be hearing aid and/or cochlear implant users, music appreciation can be challenging. Research highlights difficulties with pitch and melodic perception, problems identifying instruments and lyrics, distortion and poor sound quality. This panel will critically discuss the key factors influencing music appreciation for those with and without hearing loss. After a brief discussion of motivations for engaging with music, the panel will consider the musical, listener and contextual factors that shape our responses to music and patterns of preference. The panellists, who have knowledge and expertise in music, performance, psychology, acoustics and audiology, will reflect on their own musical experiences and how these are shaped by musical contexts and changes in hearing. The discussion will broaden to assess how music experiences might be improved for those with hearing loss, considering hearing devices, technological innovation and clinical practice.
Future development of AI for enhancing music for listeners with hearing loss (Chair: William Whitmer), Friday June 21st, 2024
In this panel session, there will be a discussion of the future development of Artificial Intelligence (AI) for enhancing music listening for people with hearing loss. Currently, there is an accessibility gap in music listening for individuals with hearing loss. In the Cadenza project, the team is running signal processing challenges aimed at improving hearing aid technology specifically for music listening. Generally, hearing aids amplify all sound; this strategy is suboptimal for speech enhancement and for music listening. Hearing aid wearers often turn off their device or don’t make use of a specific music setting on their hearing aids, as the existing technology degrades their music listening experience.
In this session, the panel will discuss emerging trends in AI-driven methodologies such as sound source separation, equalisation and personalised audio rendering that can be used to address the auditory challenges faced by this growing population. The discussion will be informed by what has been learned in the Cadenza project. Another topic of discussion will be the integration of AI algorithms into hearing aids for real-time adaptive music processing, offering customisable listening experiences tailored to individual hearing profiles. We need to find an objective metric that can be used to configure music processing algorithms, for cases when running listening tests is not feasible. Music listening for people with hearing loss is a multidisciplinary problem that, if solved, will enhance the quality of life of hearing aid wearers.
VCCA2024 Links
Find out more: