Metraipolis › archive › dc_ab810fc592a5
Improving the Dependency on Fine-Tuning Data in Transfer Learning for Speech Emotion Recognition — arXiv:2610.38050
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38050
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T03:01:07.903Z
- SHA-256 of the archived text
d8e2043b3e5b469490ebf5a95535803e79b2741958569b14128e84195b237696- Stable URL of this page
https://metraipolis.com/documento/dc_ab810fc592a5
How to cite
Improving the Dependency on Fine-Tuning Data in Transfer Learning for Speech Emotion Recognition — arXiv:2610.38050 — arXiv (en), https://arxiv.org/abs/2610.38050 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ab810fc592a5 (Metraipolis archive dc_ab810fc592a5, sha256 d8e2043b3e5b469490ebf5a95535803e79b2741958569b14128e84195b237696)
BibTeX
@misc{dcab810fc592a5,
title = {Improving the Dependency on Fine-Tuning Data in Transfer Learning for Speech Emotion Recognition — arXiv:2610.38050},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38050},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ab810fc592a5; sha256 d8e2043b3e5b469490ebf5a95535803e79b2741958569b14128e84195b237696},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38050. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Compensating for train-test mismatches in acoustic environments is important for deployable speech solutions. This paper proposes to reduce the amount of fine-tuning data needed in transfer learning to mitigate the train-test mismatch by using a compensation mechanism based on the feature maximum likelihood linear regression (fMLLR) algorithm. Our scheme incorporates an autoencoder to reduce the number of trainable parameters. Operating on the encoder latent space, our compensation strategy employs an affine linear transform that accounts for rotations and shifts in the feature space. We evaluate the proposed solution in a speech emotion recognition (SER) task within a realistic human-robot interaction scenario. The results show that the proposed architecture outperforms the original scheme without the compensation strategy. We observe a performance gain in the mean concordance correlation coefficient (CCC) of 16.8% using 12.9% of the training set, and 14.4% using 50% of the training set. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno). Categorie arXiv: Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2610.38050 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-01T02:26:00.564Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).