@inproceedings{wang-etal-2026-semg,
title = "s{EMG} Typing Transcription with Conformer Encoding and Beam-Aware Large Language Model Correction",
author = "Wang, Yuanxi and
Shu, Lun and
Koike, Yasuharu",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.598/",
pages = "13763--13780",
ISBN = "979-8-89176-459-0",
abstract = "Surface electromyography (sEMG) offers a promising path toward private and wearable text input, but accurate typing transcription remains challenging due to strong cross-user and cross-session variability. We propose a beam-aware sEMG typing framework that connects an improved Connectionist Temporal Classification (CTC)-based frontend with a large language model (LLM) corrector for exact recovery of the typed sequence. As a standalone sEMG decoder, our CNN-Conformer frontend achieves the best reported performance among the compared published emg2qwerty systems under the full-session frontend protocol, reaching 19.94{\%} generic character error rate (CER) and 3.43{\%} personalized CER. For LLM correction, we use a separate windowed hypothesis-export protocol, where the frontend{'}s top-10 CTC hypotheses are provided to a fine-tuned LLM together with a rank-1 baseline. Under this within-protocol comparison, the LLM reduces session-level CER from 22.53{\%} to 19.65{\%} in the generic setting and from 3.41{\%} to 2.01{\%} after personalization. A matched hybrid evaluation further confirms that the LLM also improves rank-1 outputs obtained from full-session decoding. The top-10 oracle results show that the beam contains recoverable information beyond the rank-1 output. These results demonstrate that a stronger sEMG frontend and hypothesis-aware LLM correction can work together effectively for exact sEMG typing transcription."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-semg">
<titleInfo>
<title>sEMG Typing Transcription with Conformer Encoding and Beam-Aware Large Language Model Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuanxi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lun</namePart>
<namePart type="family">Shu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasuharu</namePart>
<namePart type="family">Koike</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Surface electromyography (sEMG) offers a promising path toward private and wearable text input, but accurate typing transcription remains challenging due to strong cross-user and cross-session variability. We propose a beam-aware sEMG typing framework that connects an improved Connectionist Temporal Classification (CTC)-based frontend with a large language model (LLM) corrector for exact recovery of the typed sequence. As a standalone sEMG decoder, our CNN-Conformer frontend achieves the best reported performance among the compared published emg2qwerty systems under the full-session frontend protocol, reaching 19.94% generic character error rate (CER) and 3.43% personalized CER. For LLM correction, we use a separate windowed hypothesis-export protocol, where the frontend’s top-10 CTC hypotheses are provided to a fine-tuned LLM together with a rank-1 baseline. Under this within-protocol comparison, the LLM reduces session-level CER from 22.53% to 19.65% in the generic setting and from 3.41% to 2.01% after personalization. A matched hybrid evaluation further confirms that the LLM also improves rank-1 outputs obtained from full-session decoding. The top-10 oracle results show that the beam contains recoverable information beyond the rank-1 output. These results demonstrate that a stronger sEMG frontend and hypothesis-aware LLM correction can work together effectively for exact sEMG typing transcription.</abstract>
<identifier type="citekey">wang-etal-2026-semg</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.598/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>13763</start>
<end>13780</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T sEMG Typing Transcription with Conformer Encoding and Beam-Aware Large Language Model Correction
%A Wang, Yuanxi
%A Shu, Lun
%A Koike, Yasuharu
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F wang-etal-2026-semg
%X Surface electromyography (sEMG) offers a promising path toward private and wearable text input, but accurate typing transcription remains challenging due to strong cross-user and cross-session variability. We propose a beam-aware sEMG typing framework that connects an improved Connectionist Temporal Classification (CTC)-based frontend with a large language model (LLM) corrector for exact recovery of the typed sequence. As a standalone sEMG decoder, our CNN-Conformer frontend achieves the best reported performance among the compared published emg2qwerty systems under the full-session frontend protocol, reaching 19.94% generic character error rate (CER) and 3.43% personalized CER. For LLM correction, we use a separate windowed hypothesis-export protocol, where the frontend’s top-10 CTC hypotheses are provided to a fine-tuned LLM together with a rank-1 baseline. Under this within-protocol comparison, the LLM reduces session-level CER from 22.53% to 19.65% in the generic setting and from 3.41% to 2.01% after personalization. A matched hybrid evaluation further confirms that the LLM also improves rank-1 outputs obtained from full-session decoding. The top-10 oracle results show that the beam contains recoverable information beyond the rank-1 output. These results demonstrate that a stronger sEMG frontend and hypothesis-aware LLM correction can work together effectively for exact sEMG typing transcription.
%U https://aclanthology.org/2026.emnlp-main.598/
%P 13763-13780
Markdown (Informal)
[sEMG Typing Transcription with Conformer Encoding and Beam-Aware Large Language Model Correction](https://aclanthology.org/2026.emnlp-main.598/) (Wang et al., EMNLP 2026)
ACL