Machine Learning Challenges for Hearing Aids (Clarity-2024)
5th December 2024, Virtual Workshop
One of the biggest challenges for hearing-impaired listeners is understanding speech in the presence of background noise. Everyday social noise levels can have a devastating impact on speech intelligibility. Inability to communicate effectively can lead to social withdrawal and isolation. Disabling hearing impairment affects 360 million people worldwide, with that number increasing because of the ageing population. Unfortunately, current hearing aid technology is often ineffective in noisy situations. Although amplification can restore audibility, it does not compensate fully for the effects of hearing loss.
The aim of this virtual workshop is to report on the 3rd Clarity Enhancement Challenge (CEC3), the third in a series of machine learning challenges targeted at helping those with a hearing impairment. CEC3 has increased the complexity beyond the previous CEC2 challenge by introducing tasks with real room acoustics, real hearing aid microphone recordings and recordings of complex acoustic scenes. Systems are being evaluated using both objective measures and listening tests.
The challenge was launched in April 2024 and ran until September 2024 and has attracted submissions from US, Europe, Japan and China.
This virtual workshop will feature
- announcement of the challenge results
- presentations from participating teams
- a keynote talk
- award of prizes for best system
- a discussion of future directions for hearing aid machine learning challenges.
Programme details now available.
Organisers
- Michael Akeroyd
University of Nottingham - Jon Barker
University of Sheffield - Trevor Cox
University of Salford - John Culling
University of Cardiff - Simone Graetzer
University of Salford - Graham Naylor
University of Nottingham - Jennifer Firth
University of Nottingham - Jianyuan Sun
University of Sheffield - More info
Invited Speakers
- Stefan Raufer
Sonova AG, Switzerland - Peter Derleth
Sonova AG, Switzerland - More info