Skip to content
AI News HubLIVE
Original source2 min read

AVERT: Audio-Verified Adjudication for Spoken Dialogue State Tracking

Summary

AVERT combines cross-turn agreement voting with an audio-conditioned verifier to correct three recoverable error types left by a strong per-turn text editor in spoken dialogue state tracking.

SourcearXiv Computational LinguisticsAuthor: Chunggi Lee, Hanspeter Pfister
AVERT: Audio-Verified Adjudication for Spoken Dialogue State Tracking
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 1 Sep 2026]

Title:AVERT: Audio-Verified Adjudication for Spoken Dialogue State Tracking

View a PDF of the paper titled AVERT: Audio-Verified Adjudication for Spoken Dialogue State Tracking, by Chunggi Lee and Hanspeter Pfister

View PDF HTML (experimental)

Abstract:Spoken dialogue state tracking recovers slot-value pairs from speech, where ASR errors concentrate in entity values and persist across turns, making it both a generation and an editing problem. A strong per-turn text editor corrects much of this but, operating on the transcript alone, leaves three recoverable errors: a value predicted inconsistently across turns, an omitted slot, and a value the audio does not support. We present AVERT, which scores each candidate value by combining cross-turn agreement with a trained audio-conditioned verifier and resolves the three error types with three operators, vote, add, and swap, each restricted to the slots where its error is common. On SpokenWOZ, a base speech-LLM reaches 33.04 JGA, a text editor 38.34, and AVERT 40.13, without retraining either. This is in the range of a 1B end-to-end system that consumes the full spoken history (39.32), though AVERT uses two 1B decoders rather than one. The audio verifier contributes a statistically significant gain, and restricting each operator to a selected slot subset matters: removing it lets unrestricted voting overwrite correct categorical values and fall below the editor.

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2609.01828 [cs.CL]

(or arXiv:2609.01828v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2609.01828

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Chunggi Lee [view email] [v1] Tue, 1 Sep 2026 20:01:59 UTC (277 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled AVERT: Audio-Verified Adjudication for Spoken Dialogue State Tracking, by Chunggi Lee and Hanspeter Pfister

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • An audio verifier provides a statistically significant gain over transcript-only editing.
  • Restricting vote, add, and swap operators to selected slot subsets is critical; unrestricted voting can overwrite correct categorical values.
  • On SpokenWOZ, AVERT raises a base speech-LLM from 33.04 to 40.13 JGA without retraining either model.

Highlights and analysis are generated automatically and may contain errors. Check the original source.