Metraipolis › archive › dc_54bd8a205a7a

ToneCL: Contrastive Learning for Few-Shot Syllable-Level Tone Classification — arXiv:2609.24903

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24903
License (as archived)
CC0-1.0
Archived
2026-10-09T06:50:16.689Z
SHA-256 of the archived text
365117ca7417c2a8e506c47365b65bfc25d214d9dc824f496d1759dcefe4df80
Stable URL of this page
https://metraipolis.com/documento/dc_54bd8a205a7a

How to cite

ToneCL: Contrastive Learning for Few-Shot Syllable-Level Tone Classification — arXiv:2609.24903 — arXiv (en), https://arxiv.org/abs/2609.24903 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_54bd8a205a7a (Metraipolis archive dc_54bd8a205a7a, sha256 365117ca7417c2a8e506c47365b65bfc25d214d9dc824f496d1759dcefe4df80)
BibTeX
@misc{dc54bd8a205a7a,
  title = {ToneCL: Contrastive Learning for Few-Shot Syllable-Level Tone Classification — arXiv:2609.24903},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24903},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_54bd8a205a7a; sha256 365117ca7417c2a8e506c47365b65bfc25d214d9dc824f496d1759dcefe4df80},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24903. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tone languages constitute over 50-70% of the world's languages, but the vast majority are low-resource, lacking the large transcribed corpora needed for automatic tone classification. Existing datasets are typically collected at the sentence level, whereas field linguists require fine-grained syllable-level annotations. We propose ToneCL, a lightweight contrastive learning framework for few-shot syllable-level tone classification. We simulate low-resource conditions on Mandarin and Vietnamese, limiting labeled data to tens of examples per tone class. ToneCL is pretrained on unlabeled speech with augmentations that preserve tonal identity, then fine-tuned on few-shot examples. Experiments show our method consistently outperforms baselines, achieving 91.6% on six-speaker Mandarin at 10 shots. Cross-lingual transfer is also effective: pretraining on Vietnamese and fine-tuning on Mandarin reaches 91.0\% accuracy at 10 shots. Ablation confirms that frequency band rejection is the most critical augmentation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.24903 — 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 2026-10-09T06:48:45.071Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).