logo Idiap Research Institute        
 [BibTeX] [Marc21]
Low-Level Physiological Implications of End-to-End Learning for Speech Recognition
Type of publication: Conference paper
Citation: CoppietersdeGibson_INTERSPEECH_2022
Booktitle: Proc. Interspeech 2022
Year: 2022
Pages: 749--753
ISSN: 2308-457X
DOI: 10.21437/Interspeech.2022-10093
Abstract: Current speech recognition architectures perform very well from the point of view of machine learning, hence user interaction. This suggests that they are emulating the human biological system well. We investigate whether the inference can be inverted to provide insights into that biological system; in particular the hearing mechanism. Using SincNet, we confirm that end-to-end systems do learn well known filterbank structures. However, we also show that wider band-width filters are important in the learned structure. Whilst some benefits can be gained by initialising both narrow and wide-band filters, physiological constraints suggest that such filters arise in mid-brain rather than the cochlea. We show that standard machine learning architectures must be modified to allow this process to be emulated neurally.
Keywords: cochlear models, end-to-end architectures, filterbanks, SincNet, speech recognition
Authors Coppieters de Gibson, Louise
Garner, Philip N.
Added by: [UNK]
Total mark: 0
  • CoppietersdeGibson_INTERSPEECH_2022.pdf