<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vu-etal-2026-streamcorrect">
    <titleInfo>
        <title>StreamCorrect: Self-Supervised Error Correction for Real-Time ASR with Offline Recognizers</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tung</namePart>
        <namePart type="given">D</namePart>
        <namePart type="family">Vu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zeying</namePart>
        <namePart type="family">Xie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Weiwei</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Victor</namePart>
        <namePart type="given">Junqiu</namePart>
        <namePart type="family">Wei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Di</namePart>
        <namePart type="family">Jiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi</namePart>
        <namePart type="given">R</namePart>
        <namePart type="family">Fung</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: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Pepa</namePart>
            <namePart type="family">Atanasova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gholamreza</namePart>
            <namePart type="family">Haffari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Minghan</namePart>
            <namePart type="family">Wang</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">979-8-89176-460-6</identifier>
    </relatedItem>
    <abstract>Streaming Automatic Speech Recognition (ASR), also known as online or real-time ASR, transcribes speech incrementally while audio is being spoken and is critical for many industry applications. Despite the strong performance of modern offline ASR models, streaming deployment remains challenging because limited future context can cause early recognition errors to propagate across later chunks. We define the task of streaming ASR error correction and propose StreamCorrect, a modular framework that fine-tunes a lightweight error corrector from self-generated streaming ASR errors and integrates it with existing streaming ASR systems. To enable training without human annotation, StreamCorrect introduces a timestamp-free boundary recovery procedure based on Prefix-to-Reference Alignment for generating chunk-level correction data. Across multiple languages and ASR backbones, StreamCorrect achieves up to 39% relative character error rate (CER) reduction with minimal latency overhead. Error propagation analysis further shows increasing benefits over time, with up to 7.2% absolute CER reduction in later audio chunks. StreamCorrect bridges offline ASR models and streaming deployment through a lightweight correction plug-in while preserving the pretrained ASR component without additional tuning or distillation.</abstract>
    <identifier type="citekey">vu-etal-2026-streamcorrect</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.142/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2391</start>
            <end>2403</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T StreamCorrect: Self-Supervised Error Correction for Real-Time ASR with Offline Recognizers
%A Vu, Tung D.
%A Xie, Zeying
%A Zhao, Weiwei
%A Wei, Victor Junqiu
%A Jiang, Di
%A Fung, Yi R.
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F vu-etal-2026-streamcorrect
%X Streaming Automatic Speech Recognition (ASR), also known as online or real-time ASR, transcribes speech incrementally while audio is being spoken and is critical for many industry applications. Despite the strong performance of modern offline ASR models, streaming deployment remains challenging because limited future context can cause early recognition errors to propagate across later chunks. We define the task of streaming ASR error correction and propose StreamCorrect, a modular framework that fine-tunes a lightweight error corrector from self-generated streaming ASR errors and integrates it with existing streaming ASR systems. To enable training without human annotation, StreamCorrect introduces a timestamp-free boundary recovery procedure based on Prefix-to-Reference Alignment for generating chunk-level correction data. Across multiple languages and ASR backbones, StreamCorrect achieves up to 39% relative character error rate (CER) reduction with minimal latency overhead. Error propagation analysis further shows increasing benefits over time, with up to 7.2% absolute CER reduction in later audio chunks. StreamCorrect bridges offline ASR models and streaming deployment through a lightweight correction plug-in while preserving the pretrained ASR component without additional tuning or distillation.
%U https://aclanthology.org/2026.emnlp-industry.142/
%P 2391-2403

Markdown (Informal)

[StreamCorrect: Self-Supervised Error Correction for Real-Time ASR with Offline Recognizers](https://aclanthology.org/2026.emnlp-industry.142/) (Vu et al., EMNLP 2026)

• StreamCorrect: Self-Supervised Error Correction for Real-Time ASR with Offline Recognizers (Vu et al., EMNLP 2026)

ACL

• Tung D. Vu, Zeying Xie, Weiwei Zhao, Victor Junqiu Wei, Di Jiang, and Yi R. Fung. 2026. StreamCorrect: Self-Supervised Error Correction for Real-Time ASR with Offline Recognizers. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 2391–2403, Budapest, Hungary. Association for Computational Linguistics.