Metraipolis › archive › dc_338692d339bd

PhonoBridge: Error-Aware Phoneme-Mediated EMG-to-Text Reconstruction — arXiv:2610.27678

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.27678
License (as archived)
CC0-1.0
Archived
2026-10-21T07:09:18.413Z
SHA-256 of the archived text
1026f99b46b071977aa2e09e657cbffd24bd93fd85cc2b804255ac8a8a00dc37
Stable URL of this page
https://metraipolis.com/documento/dc_338692d339bd

How to cite

PhonoBridge: Error-Aware Phoneme-Mediated EMG-to-Text Reconstruction — arXiv:2610.27678 — arXiv (en), https://arxiv.org/abs/2610.27678 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_338692d339bd (Metraipolis archive dc_338692d339bd, sha256 1026f99b46b071977aa2e09e657cbffd24bd93fd85cc2b804255ac8a8a00dc37)
BibTeX
@misc{dc338692d339bd,
  title = {PhonoBridge: Error-Aware Phoneme-Mediated EMG-to-Text Reconstruction — arXiv:2610.27678},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.27678},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_338692d339bd; sha256 1026f99b46b071977aa2e09e657cbffd24bd93fd85cc2b804255ac8a8a00dc37},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27678. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Electromyography (EMG) provides a non-invasive means of decoding silently articulated speech into text, but accurate decoding remains challenging due to limited availability of paired EMG-text data. We introduce PhonoBridge, a two-stage framework comprising a channel-aware EMG-to-phoneme frontend and a large language model (LLM) backend for text reconstruction. The frontend is trained on paired EMG-text data that consists of channel-wise feature extraction, cross-channel fusion, and electrode embeddings. With phonemes as the intermediate representation, we expand the backend's training data by converting LibriSpeech transcripts into phoneme-text pairs without additional EMG recordings. To adapt the LLM to frontend noise, we introduce Error-Profile-Guided Augmentation (EPGA), which perturbs transcript-derived phoneme sequences according to error patterns estimated from frontend predictions, generating additional training pairs for the LLM. On the Open Vocabulary silent-speech dataset, PhonoBridge achieves 24.77% WER, outperforming the previously reported best of 28.27% on the same test split.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Sound (cs.SD) ; Computation and Language (cs.CL); Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2610.27678 — 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 2026-10-21T07:05:58.172Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).