English

Using Speech Foundational Models in Loss Functions for Hearing Aid Speech Enhancement

Sound 2024-07-19 v1 Audio and Speech Processing

Abstract

Machine learning techniques are an active area of research for speech enhancement for hearing aids, with one particular focus on improving the intelligibility of a noisy speech signal. Recent work has shown that feature encodings from self-supervised speech representation models can effectively capture speech intelligibility. In this work, it is shown that the distance between self-supervised speech representations of clean and noisy speech correlates more strongly with human intelligibility ratings than other signal-based metrics. Experiments show that training a speech enhancement model using this distance as part of a loss function improves the performance over using an SNR-based loss function, demonstrated by an increase in HASPI, STOI, PESQ and SI-SNR scores. This method takes inference of a high parameter count model only at training time, meaning the speech enhancement model can remain smaller, as is required for hearing aids.

Keywords

Cite

@article{arxiv.2407.13333,
  title  = {Using Speech Foundational Models in Loss Functions for Hearing Aid Speech Enhancement},
  author = {Robert Sutherland and George Close and Thomas Hain and Stefan Goetze and Jon Barker},
  journal= {arXiv preprint arXiv:2407.13333},
  year   = {2024}
}

Comments

Accepted for EUSIPCO 2024

R2 v1 2026-06-28T17:45:43.977Z