<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chattopadhyay-etal-2026-beyond">
    <titleInfo>
        <title>Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sameep</namePart>
        <namePart type="family">Chattopadhyay</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexander</namePart>
        <namePart type="family">Erdmann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mari</namePart>
        <namePart type="family">Ostendorf</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>Modern voice-agent systems rely on streaming speech recognition models that operate under stringent latency constraints. This study shows that, due to the limited memory constraints of real-time processing, these systems are adversely impacted by conversational phenomena such as long silences and backchannels. While many agentic pipelines mitigate this by resetting state at each turn, this approach discards vital context and impairs performance at turn onsets. We propose two state-management strategies that preserve cross-utterance context to reduce onset errors. In experiments with two state-of-the-art streaming models on two spoken dialogue benchmarks, our best method yields an average of 15-21% relative WER reduction at utterance onsets.</abstract>
    <identifier type="citekey">chattopadhyay-etal-2026-beyond</identifier>
    <identifier type="doi">10.18653/2026.emnlp-main.1703</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1703/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>38802</start>
            <end>38811</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents
%A Chattopadhyay, Sameep
%A Erdmann, Alexander
%A Ostendorf, Mari
%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 chattopadhyay-etal-2026-beyond
%X Modern voice-agent systems rely on streaming speech recognition models that operate under stringent latency constraints. This study shows that, due to the limited memory constraints of real-time processing, these systems are adversely impacted by conversational phenomena such as long silences and backchannels. While many agentic pipelines mitigate this by resetting state at each turn, this approach discards vital context and impairs performance at turn onsets. We propose two state-management strategies that preserve cross-utterance context to reduce onset errors. In experiments with two state-of-the-art streaming models on two spoken dialogue benchmarks, our best method yields an average of 15-21% relative WER reduction at utterance onsets.
%R 10.18653/2026.emnlp-main.1703
%U https://aclanthology.org/2026.emnlp-main.1703/
%U https://doi.org/10.18653/2026.emnlp-main.1703
%P 38802-38811

Markdown (Informal)

[Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents](https://aclanthology.org/2026.emnlp-main.1703/) (Chattopadhyay et al., EMNLP 2026)

• Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents (Chattopadhyay et al., EMNLP 2026)

ACL

• Sameep Chattopadhyay, Alexander Erdmann, and Mari Ostendorf. 2026. Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 38802–38811, Budapest, Hungary. Association for Computational Linguistics.