English

SESQA: semi-supervised learning for speech quality assessment

Audio and Speech Processing 2021-02-09 v2 Machine Learning Sound

Abstract

Automatic speech quality assessment is an important, transversal task whose progress is hampered by the scarcity of human annotations, poor generalization to unseen recording conditions, and a lack of flexibility of existing approaches. In this work, we tackle these problems with a semi-supervised learning approach, combining available annotations with programmatically generated data, and using 3 different optimization criteria together with 5 complementary auxiliary tasks. Our results show that such a semi-supervised approach can cut the error of existing methods by more than 36%, while providing additional benefits in terms of reusable features or auxiliary outputs. Improvement is further corroborated with an out-of-sample test showing promising generalization capabilities.

Keywords

Cite

@article{arxiv.2010.00368,
  title  = {SESQA: semi-supervised learning for speech quality assessment},
  author = {Joan Serrà and Jordi Pons and Santiago Pascual},
  journal= {arXiv preprint arXiv:2010.00368},
  year   = {2021}
}

Comments

Long version (with appendix) of the paper with the same title accepted for ICASSP2021

R2 v1 2026-06-23T18:56:04.730Z