Metraipolis › archive › dc_22e5154cf167
Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge — arXiv:2609.23462
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.23462
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:50:36.203Z
- SHA-256 of the archived text
955b88fbd08d8b45cb47c8501b94b94ec7837e1d9574b4779ee6d29a8a93a7d0- Stable URL of this page
https://metraipolis.com/documento/dc_22e5154cf167
How to cite
Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge — arXiv:2609.23462 — arXiv (en), https://arxiv.org/abs/2609.23462 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_22e5154cf167 (Metraipolis archive dc_22e5154cf167, sha256 955b88fbd08d8b45cb47c8501b94b94ec7837e1d9574b4779ee6d29a8a93a7d0)
BibTeX
@misc{dc22e5154cf167,
title = {Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge — arXiv:2609.23462},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.23462},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_22e5154cf167; sha256 955b88fbd08d8b45cb47c8501b94b94ec7837e1d9574b4779ee6d29a8a93a7d0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23462. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Non-verbal vocalizations (NVVs) carry important paralinguistic information but are often omitted by conventional automatic speech recognition (ASR) systems. The ISCSLP NVVSpeech Challenge requires joint transcription of lexical content and 16 NVV categories under limited and highly imbalanced supervision. We present a data-centric NVV-aware ASR pipeline based on cross-dataset label harmonization and a two-stage sampling schedule. We map heterogeneous source labels to the official taxonomy and exclude samples without a reliable mapping. Our schedule first uses square-root category sampling to moderate the long-tailed distribution and then applies uniform-category fine-tuning. On a fixed local validation split, square-root category sampling performs best among the tested single-stage settings. The final two-stage system obtains an official score of 63.86 and ranks fourth in Track 1. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL). Categorie arXiv: Audio and Speech Processing (eess.AS) ; Computation and Language (cs.CL); Sound (cs.SD). Pagina del lavoro: https://arxiv.org/abs/2609.23462 — 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 2026-10-09T06:48:45.125Z 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).