@inproceedings{das-etal-2026-audio,
title = "Audio Front-End Decoupling: Why Synthetic-Voice Simulators Fail to Predict Real-World Voice Agent Behavior",
author = "Das, Shoutrik and
Agrawal, Suraj and
Sachdeva, Aashraya",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.226/",
pages = "3781--3801",
ISBN = "979-8-89176-460-6",
abstract = "LLM-based voice agents are routinely cleared for deployment using synthetic audio regression suites, with engineering teams treating augmented commercial TTS as a safe proxy for real human callers. This paper presents the first systematic approach to quantify the profound behavioral drift that occurs when agents optimized on simulated audio are deployed in the real world. We demonstrate that the assumption of acoustic equivalence fundamentally fails: real production audio triggers 2-13 times more VAD misfires than synthetic data across Silero, WebRTC, and TEN-VAD, while simulated environments cause text-grounded turn detectors to artificially flip decisions 33{\%} of the time, compared to just 3{\%} in reality. A paired four-vendor TTS calibration sweep proves this misranking is structural: on every front-end component, optimizing thresholds for synthetic audio actively degrades real-world performance. To prevent teams from flying blind, we introduce a novel set of signal-layer metrics and an open-source framework to audit any simulator prior to adoption. Rather than testing the agent, our method tests the simulator against real target-domain interactions. By identifying where a simulator{'}s acoustics deviate from reality, teams can definitively know which front-end tuning decisions are safe to trust."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="das-etal-2026-audio">
<titleInfo>
<title>Audio Front-End Decoupling: Why Synthetic-Voice Simulators Fail to Predict Real-World Voice Agent Behavior</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shoutrik</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suraj</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aashraya</namePart>
<namePart type="family">Sachdeva</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>LLM-based voice agents are routinely cleared for deployment using synthetic audio regression suites, with engineering teams treating augmented commercial TTS as a safe proxy for real human callers. This paper presents the first systematic approach to quantify the profound behavioral drift that occurs when agents optimized on simulated audio are deployed in the real world. We demonstrate that the assumption of acoustic equivalence fundamentally fails: real production audio triggers 2-13 times more VAD misfires than synthetic data across Silero, WebRTC, and TEN-VAD, while simulated environments cause text-grounded turn detectors to artificially flip decisions 33% of the time, compared to just 3% in reality. A paired four-vendor TTS calibration sweep proves this misranking is structural: on every front-end component, optimizing thresholds for synthetic audio actively degrades real-world performance. To prevent teams from flying blind, we introduce a novel set of signal-layer metrics and an open-source framework to audit any simulator prior to adoption. Rather than testing the agent, our method tests the simulator against real target-domain interactions. By identifying where a simulator’s acoustics deviate from reality, teams can definitively know which front-end tuning decisions are safe to trust.</abstract>
<identifier type="citekey">das-etal-2026-audio</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.226/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3781</start>
<end>3801</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Audio Front-End Decoupling: Why Synthetic-Voice Simulators Fail to Predict Real-World Voice Agent Behavior
%A Das, Shoutrik
%A Agrawal, Suraj
%A Sachdeva, Aashraya
%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 das-etal-2026-audio
%X LLM-based voice agents are routinely cleared for deployment using synthetic audio regression suites, with engineering teams treating augmented commercial TTS as a safe proxy for real human callers. This paper presents the first systematic approach to quantify the profound behavioral drift that occurs when agents optimized on simulated audio are deployed in the real world. We demonstrate that the assumption of acoustic equivalence fundamentally fails: real production audio triggers 2-13 times more VAD misfires than synthetic data across Silero, WebRTC, and TEN-VAD, while simulated environments cause text-grounded turn detectors to artificially flip decisions 33% of the time, compared to just 3% in reality. A paired four-vendor TTS calibration sweep proves this misranking is structural: on every front-end component, optimizing thresholds for synthetic audio actively degrades real-world performance. To prevent teams from flying blind, we introduce a novel set of signal-layer metrics and an open-source framework to audit any simulator prior to adoption. Rather than testing the agent, our method tests the simulator against real target-domain interactions. By identifying where a simulator’s acoustics deviate from reality, teams can definitively know which front-end tuning decisions are safe to trust.
%U https://aclanthology.org/2026.emnlp-industry.226/
%P 3781-3801
Markdown (Informal)
[Audio Front-End Decoupling: Why Synthetic-Voice Simulators Fail to Predict Real-World Voice Agent Behavior](https://aclanthology.org/2026.emnlp-industry.226/) (Das et al., EMNLP 2026)
ACL