Metraipolis › archive › dc_fd7b3c24dc6c

DIY Customized Speech Recognition for a Person with Speech Disabilities — arXiv:2611.11327

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.11327
License (as archived)
CC0-1.0
Archived
2026-11-10T18:46:58.930Z
SHA-256 of the archived text
b6b98f09784bf71714c982cd55513cf4fd67ee9d53daa8980237fdefeece7990
Stable URL of this page
https://metraipolis.com/documento/dc_fd7b3c24dc6c

How to cite

DIY Customized Speech Recognition for a Person with Speech Disabilities — arXiv:2611.11327 — arXiv (en), https://arxiv.org/abs/2611.11327 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd7b3c24dc6c (Metraipolis archive dc_fd7b3c24dc6c, sha256 b6b98f09784bf71714c982cd55513cf4fd67ee9d53daa8980237fdefeece7990)
BibTeX
@misc{dcfd7b3c24dc6c,
  title = {DIY Customized Speech Recognition for a Person with Speech Disabilities — arXiv:2611.11327},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.11327},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd7b3c24dc6c; sha256 b6b98f09784bf71714c982cd55513cf4fd67ee9d53daa8980237fdefeece7990},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11327. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

General-purpose state-of-the-art automatic speech recognition (ASR) systems fail systematically for speakers with moderate to severe speech disabilities. This paper describes the design, implementation, and evaluation of a customized ASR system built for the first author, a researcher with cerebral palsy and dysarthria. We fine-tuned OpenAI's Whisper medium and large-v3 models using Low-Rank Adaptation (LoRA) on audio samples recorded from the first author's own speech on consumer-grade hardware. On a held-out test set of 100 previously unseen utterances, the corresponding transcriptions resulted in a Word Error Rate drop from 49% to 17% for medium and from 30% to 12% for large-v3, while the Character Error Rate fell from 26% to 7% for medium and from 16% to 5% for large-v3, indicating that the residual errors are minor phonemic substitutions. Based on these models, the first author developed AVoz, a mobile application that acts as a real-time interpreter, converting his speech into synthesized voice for the listener. All processing is performed locally, ensuring that no audio data leaves the user's machine. We argue that the methodology is replicable. Moreover, we publish the full LoRA configuration, the implementation, and a step-by-step recording and training protocol, so that other people with speech disabilities, or their family members and caregivers, can build their own systems with a few hours of labeled audio data and a couple of days of GPU time.

Tema degli esploratori: governance digitale e beni comuni (elenco arXiv cs.CY, nuovi lavori del giorno).
Categorie arXiv: Sound (cs.SD) ; Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2611.11327 — 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 2026-11-10T18:38:52.438Z dalla pagina https://arxiv.org/list/cs.CY/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).