Metraipolis › archive › dc_6293d10ab5fa

CORD-KWS: Calibrated, Order-Aware Detection for Open-Vocabulary Keyword Spotting — arXiv:2609.31869

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31869
License (as archived)
CC0-1.0
Archived
2026-10-08T01:37:20.642Z
SHA-256 of the archived text
b21950b6febfe7975757f0e0a5593eea2e90cb1c29bd6e07487eabcc2ab6243d
Stable URL of this page
https://metraipolis.com/documento/dc_6293d10ab5fa

How to cite

CORD-KWS: Calibrated, Order-Aware Detection for Open-Vocabulary Keyword Spotting — arXiv:2609.31869 — arXiv (en), https://arxiv.org/abs/2609.31869 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6293d10ab5fa (Metraipolis archive dc_6293d10ab5fa, sha256 b21950b6febfe7975757f0e0a5593eea2e90cb1c29bd6e07487eabcc2ab6243d)
BibTeX
@misc{dc6293d10ab5fa,
  title = {CORD-KWS: Calibrated, Order-Aware Detection for Open-Vocabulary Keyword Spotting — arXiv:2609.31869},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31869},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6293d10ab5fa; sha256 b21950b6febfe7975757f0e0a5593eea2e90cb1c29bd6e07487eabcc2ab6243d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31869. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Open-vocabulary keyword spotting (KWS) must detect arbitrary keywords without retraining. Cross-attention-based models achieve state-of-the-art performance but require pairwise interaction between the audio and each keyword, recomputing the fused representation for every audio--keyword pair. Embedding-based models avoid this computational cost through independent encoding and similarity scoring, yet remain inferior on challenging benchmarks such as LibriPhrase-hard. We show that this gap is primarily a training issue rather than a limitation of model capacity. While contrastive learning encourages correct keywords to rank above negatives, it does not explicitly calibrate absolute similarity scores, which are critical for applying a fixed threshold across keyword detection. We propose Calibrated, Order-aware Detection KWS (CORD-KWS), a training framework that introduces two complementary objectives while retaining the same encoders, cosine scoring, and O(1) keyword enrollment: a calibrated detection head that supervises absolute scores, and a frame-level CTC objective that preserves phonetic order information. CORD-KWS achieves EERs of 0.43% and 9.64% on LibriPhrase-easy and LibriPhrase-hard, respectively, outperforming existing embedding- and cross-attention-based models.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in eess.AS).
Categorie arXiv: Sound (cs.SD) ; Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.31869 — 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 2026-10-08T01:11:22.077Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).