3 papers
eess.AS2022
Auditory-Based Data Augmentation for End-to-End Automatic Speech Recognition
Zehai Tu, Jack Deadman, Ning Ma +1
End-to-end models have achieved significant improvement on automatic speech recognition. One common method to improve performance of these models is expanding the data-space throug…
cs.SD2021
Optimising Hearing Aid Fittings for Speech in Noise with a Differentiable Hearing Loss Model
Zehai Tu, Ning Ma, Jon Barker
Current hearing aids normally provide amplification based on a general prescriptive fitting, and the benefits provided by the hearing aids vary among different listening environmen…
cs.SD2021
DHASP: Differentiable Hearing Aid Speech Processing
Zehai Tu, Ning Ma, Jon Barker
Hearing aids are expected to improve speech intelligibility for listeners with hearing impairment. An appropriate amplification fitting tuned for the listener's hearing disability…