# Low-Level Physiological Implications of End-to-End Learning of Speech Recognition

arXiv: https://arxiv.org/abs/2208.11700 · HTML: https://mlsanity.com/paper/2208.11700/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 31 references that are in the map.
- First posted on arXiv 22 Aug 2022.

## Builds on (most cited first, 7 of 7)

- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [Speaker Recognition from Raw Waveform with SincNet](https://mlsanity.com/paper/1808.00158/) (2018)
- [Wav2Letter: an End-to-End ConvNet-based Speech Recognition System](https://mlsanity.com/paper/1609.03193/) (2016)
- [Learning Filterbanks from Raw Speech for Phone Recognition](https://mlsanity.com/paper/1711.01161/) (2017)
- [Estimating Phoneme Class Conditional Probabilities from Raw Speech Signal using Convolutional Neural Networks](https://mlsanity.com/paper/1304.1018/) (2013)
- [Speech and Speaker Recognition from Raw Waveform with SincNet](https://mlsanity.com/paper/1812.05920/) (2018)

## Abstract (arXiv)

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.