Metraipolis › archive › dc_4d02bc2103a8

Human-like cross-language generalisation in deep neural speaker embeddings and its acoustic foundations — arXiv:2611.05384

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05384
License (as archived)
CC0-1.0
Archived
2026-11-05T18:18:34.628Z
SHA-256 of the archived text
47de7e4be2d1bd2399a77abcad2e3c1aa944a7cf83d708dadc645c068f2c3526
Stable URL of this page
https://metraipolis.com/documento/dc_4d02bc2103a8

How to cite

Human-like cross-language generalisation in deep neural speaker embeddings and its acoustic foundations — arXiv:2611.05384 — arXiv (en), https://arxiv.org/abs/2611.05384 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4d02bc2103a8 (Metraipolis archive dc_4d02bc2103a8, sha256 47de7e4be2d1bd2399a77abcad2e3c1aa944a7cf83d708dadc645c068f2c3526)
BibTeX
@misc{dc4d02bc2103a8,
  title = {Human-like cross-language generalisation in deep neural speaker embeddings and its acoustic foundations — arXiv:2611.05384},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05384},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4d02bc2103a8; sha256 47de7e4be2d1bd2399a77abcad2e3c1aa944a7cf83d708dadc645c068f2c3526},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05384. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generalisability is a central question for deep neural networks, including the cross-language generalisation of speaker embeddings. This study examined whether deep neural speaker embeddings generalise across languages and how such generalisation relates to human perception and acoustic structure. Using Cantonese--English bilingual speech presented in within- and cross-language conditions, we derived similarity from 18 state-of-the-art models and compared it with human ratings and acoustic features using linear mixed models and representational similarity analysis. Embeddings exhibited cross-language generalisation that broadly paralleled human behaviour, reflecting accurate identity discrimination and sensitivity to language switching. This generalisation relied on largely shared acoustic cues with language-sensitive weighting, mirroring human patterns. Together, these findings provide converging evidence for human--machine alignment in cross-language voice similarity processing.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Sound (cs.SD); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2611.05384 — 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 2026-11-05T18:13:03.935Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).