# CHAT Workshop

# About

# One of the biggest challenges for hearing impaired listeners is understanding speech in the presence of background noise. Noise levels that are typical of everyday social situations can have a devastating impact on speech intelligibility. Inability to communicate effectively can lead to social withdrawal and isolation. Unfortunately, current hearing aid and cochlear implant technology is often ineffective in these situations. Although amplification can restore audibility, it does not compensate for the full effects of hearing loss.

The aim of this ISCA-supported workshop is to present the challenges of hearing aid signal processing to the wider speech science and speech technology communities. Recent advances in hearing aid hardware are presenting opportunities for increasingly sophisticated processing. For example, wireless communication between the hearing aid and a mobile device can allow non-latency critical computation to be freed from the low-power constraints attendant with traditional aids. These advances raise the prospect that the computationally demanding techniques employed with great success in statistical speech modelling and statistical acoustic scene analysis could soon be exploited for hearing aid processing.

We believe that new directions in hearing aid research can be inspired by bringing together speech technologists and hearing researchers. We anticipate that the workshop will stimulate a two-way conversation between the speech research community and hearing aid developers. Hearing aid developers, who are not typically represented at Interspeech, will have an opportunity to present the challenges of their industry to the speech community; the speech community will be able to present and discuss potentially transformative approaches to speech in noise processing in the presence of hearing researchers and industry experts.

# Topics

Any work related to the challenges of hearing aid signal processing will be considered relevant. Particular topics of interest include, but are not limited to,

• New directions in multimodal hearing technology
• Models of speech intelligibility for normal and hearing impaired listeners
• Applications of auditory scene analysis
• Binaural technology for speech enhancement and source separation
• Microphone and multi-microphone technology
• Low-latency approaches to speech intelligibility enhancement
• Statistical model-driven approaches to hearing aid processing
• Emerging Audio-visual (AV) approaches to speech enhancement
• Quality & Intelligibility Assessment of audio for HA/CI users

# Venue

# Submission

# Organizers

# Workshop Chairs

• Jon Barker, University of Sheffield, UK
• Amir Hussain, Edinburgh Napier University, UK
• Peter Bell, University of Edinburgh, UK

# Sponsors

The Workshop has been made possible by financial support from the UK Engineering and Physical Research Council, the UK Medical Research Council and the International Speech Communication Association.