Improving speech-in-noise for hearing devices (Clarity-2025)
22nd August 2025, Rotterdam, The Netherlands
We are now pleased to announce the 6th Clarity Workshop for Improving Speech-in-Noise for Hearing Devices, to be collocated with Interspeech 2025, Rotterdam, The Netherlands. This will be an in-person Clarity event, following the format of the 4th Clarity workshop that was a satellite of Interspeech 2023.About
Understanding speech in noisy environments is a significant challenge—not only for individuals with hearing impairment but also for users of hearables, communication headsets, and consumer audio devices. Background noise in social settings can drastically reduce speech intelligibility, increasing listening effort and diminishing overall communication clarity. While this issue is particularly critical for the over 360 million people worldwide with disabling hearing impairment, speech enhancement technologies also benefit professionals working in noisy environments and users of augmented listening devices seeking improved auditory experiences.
Recent advances in machine learning, digital signal processing (DSP), and edge AI have enabled groundbreaking solutions for both hearing aids and next-generation hearables. Low-power AI models now provide real-time speech enhancement on hearing aids, hearables, and earbuds, while wireless connectivity allows cloud-assisted processing without sacrificing battery life. Additionally, speech separation, statistical speech modeling, and acoustic scene analysis are being integrated into consumer listening devices, enhancing speech intelligibility in noisy environments.
The Clarity Workshop brings together researchers, engineers, and industry professionals working at the intersection of speech processing, auditory perception, and assistive technology. Whether your focus is on traditional hearing aids, hearables, or AI-powered speech enhancement, we invite you to join the discussion on the next generation of speech-in-noise solutions.
Topics
We welcome any work related to speech-in-noise processing for hearing enhancement devices, including (but not limited to) the following areas:
- Binaural technology for speech enhancement and source separation
- Multi-microphone processing techniques
- Real-time and low-latency approaches to speech enhancement
- Statistical model-driven approaches to hearing aid processing
- Machine learning approaches for personalising amplification
- Machine learning models of hearing impairment
- DNN-based speech enhancement under model size and low power constraints
- Audio quality and intelligibility assessment for hearing aid, cochlear implant, and hearable users
- Efficient integration of psychoacoustic testing in machine learning
The 3rd Clarity Prediction Challenge
Clarity-2025 will host the 3rd Clarity Prediction Challenge, focused on developing innovative intrusive and non-intrusive methods for predicting hearing-aid speech intelligibility. The Challenge launches on 1st March. If you’re interested in participating, please sign up for our Google group to receive further updates.
Organisers
- Michael Akeroyd
University of Nottingham, UK - Jon Barker
University of Sheffield, UK - Fei Chen
Southern University of Science and Tech., China - Trevor Cox
University of Salford, UK - John Culling
University of Cardiff, UK - Jennifer Firth
University of Nottingham, UK - Simone Graetzer
University of Salford, UK - Graham Naylor
University of Nottingham, UK - Jordi de Vries
TU Ghent, The Netherlands - More info
Keynote Speakers
- Announcements coming soon!
Invited Talks
- Announcements coming soon!
Registration
- Registration opens in April 2025.