Metraipolis › archive › dc_7b4e1f931cb5
VoxLock: Target-Speaker Extraction for Voice Agents Without an Enrollment Step — arXiv:2610.40727
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40727
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T08:32:59.303Z
- SHA-256 of the archived text
78f1b3af1a503e0cb5da41b3daad663b25be2d53d47699e7a1dbe01533bf758d- Stable URL of this page
https://metraipolis.com/documento/dc_7b4e1f931cb5
How to cite
VoxLock: Target-Speaker Extraction for Voice Agents Without an Enrollment Step — arXiv:2610.40727 — arXiv (en), https://arxiv.org/abs/2610.40727 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b4e1f931cb5 (Metraipolis archive dc_7b4e1f931cb5, sha256 78f1b3af1a503e0cb5da41b3daad663b25be2d53d47699e7a1dbe01533bf758d)
BibTeX
@misc{dc7b4e1f931cb5,
title = {VoxLock: Target-Speaker Extraction for Voice Agents Without an Enrollment Step — arXiv:2610.40727},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40727},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b4e1f931cb5; sha256 78f1b3af1a503e0cb5da41b3daad663b25be2d53d47699e7a1dbe01533bf758d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40727. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A voice agent's speech recognizer transcribes everyone near the microphone, including people other than the caller. I fine-tuned a public causal target-speaker extraction model (REAL-TSE, 27M parameters) on one GPU to work from a voice sample cut from the call itself, and released it as VoxLock. I score it by what a recognizer writes on real recordings. On Krisp's 265-recording benchmark it reaches 4.95% WER against 23.21% unprocessed and lets 9 background words into the transcript over 85 minutes of background-only speech. Its WER is not significantly different from Krisp's best filters and is significantly lower than the other commercial and open systems I tested. On 400 AMI meeting windows built and frozen before scoring, it cuts WER from 42.95% to 10.63%. The 8-bit model runs a live call on 77% of one CPU thread with 24 ms of algorithmic latency. Model, code and per-file scores are open. 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/2610.40727 — 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 2026-11-03T08:15:54.216Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).