Prof Trevor Cox's Outputs (8)

The 1st Clarity Prediction Challenge: A machine learning challenge for hearing aid intelligibility prediction (2022)
Presentation / Conference Contribution

This paper reports on the design and outcomes of the 1st Clarity Prediction Challenge (CPC1) for predicting the intelligibility of hearing aid processed signals heard by individuals with a hearing impairment. The challenge was designed to promote the... Read More about The 1st Clarity Prediction Challenge: A machine learning challenge for hearing aid intelligibility prediction.

Inventive Podcast: Evaluation of Project Participants (2022)
Other
Harris, L., & Cox, T. (2022). Inventive Podcast: Evaluation of Project Participants. Salford

The Inventive podcast project was devised as a novel format for 'mixing engineering fact & fiction': Each episode features both an engineer being interviewed, and a fictional piece created by a writer in response to that interview. The project aims... Read More about Inventive Podcast: Evaluation of Project Participants.

Speech-To-Screen raw data zip file (2022)
Data

Speech-To-Screen listening experiment - raw data
Zip file containing 100 x .mat files (Matlab)
See also separate ReadMe text file for further details

20 participants, 5 files each:
* 1 x practice session
* 4 x actual sessions: SMN_0; SMN_1; SS... Read More about Speech-To-Screen raw data zip file.

Read Me info for Speech-To-Screen raw data zip file (2022)
Data

.txt file with information relating to the S2S Raw Data zip file.


Note that:

INT: Speech internalised; Noise internalised.

SN: Speech internalised; Noise externalised (at screen).

NS: Speech externalised (at screen); Noise internalised.... Read More about Read Me info for Speech-To-Screen raw data zip file.

Speech-To-Screen collated correct word percentages (2022)
Data

.txt file containing results from the 'Speech-To-Screen listening experiment collated as correct word percentages.

20 x participants (s1-s20)
16 x combination of conditions tested per participant:
- 2 x masking noise types: SSN and SMN
- 2 x vi... Read More about Speech-To-Screen collated correct word percentages.

Improving the measurement and acoustic performance of transparent face masks and shields (2022)
Journal Article
Cox, T. J., Dodgson, G., Harris, L., Perugia, E., Stone, M. A., & Walsh, M. (2022). Improving the measurement and acoustic performance of transparent face masks and shields. ˜The œJournal of the Acoustical Society of America (Online), 151(5), 2931-2944. https://doi.org/10.1121/10.0010384

Opaque face masks harm communication by preventing speech-reading (lip-reading) and attenuating high-frequency sound. Although transparent masks and shields (visors) with clear plastic inserts allow speech-reading, they usually create more sound atte... Read More about Improving the measurement and acoustic performance of transparent face masks and shields.

Dataset of British English speech recordings for psychoacoustics and speech processing research : the Clarity Speech Corpus (2022)
Journal Article

This paper presents the Clarity Speech Corpus, a publicly available, forty speaker British English speech dataset. The corpus was created for the purpose of running listening tests to gauge speech intelligibility and quality in the Clarity Project, w... Read More about Dataset of British English speech recordings for psychoacoustics and speech processing research : the Clarity Speech Corpus.

Improving the measurement and acoustic performance of transparent face masks and shields (2022)
Data

This is the raw measured data that is analysed and presented in: T. J. Cox , G. Dodgson, L. Harris, E. Perugia, M. A. Stone, M. Walsh, Improving the measurement and acoustic performance of transparent face masks and shields, Journal of the Acoustical... Read More about Improving the measurement and acoustic performance of transparent face masks and shields.