Skip to content
AI News HubLIVE
Original source2 min read

The Anatomy of an ASR Hallucination

Summary

A new paper investigates why automatic speech recognition (ASR) systems produce fluent text unrelated to the input speech. By analyzing two independently trained Conformer-Large models (CTC and RNN-T) under environmental degradation and speaker-background shift, the authors find that the final encoder stage is a critical boundary: bypassing it causes divergence on nearly every utterance, while bypassing middle blocks has little effect. At this stage, representations become more compact, text becomes readable by the decoder, and grapheme information becomes explicit. However, the intervention yields garbled or repetitive output rather than fluent fabrication, so the study identifies a mechanistic precondition for hallucination—failure to produce adequately grounded output—not the complete…

SourcearXiv Computational LinguisticsAuthor: Hamees Sayed, Apoorv Singh, Kumar Aman, Akshat Mandloi
The Anatomy of an ASR Hallucination
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 3 Sep 2026]

Title:The Anatomy of an ASR Hallucination

View a PDF of the paper titled The Anatomy of an ASR Hallucination, by Hamees Sayed and 3 other authors

View PDF HTML (experimental)

Abstract:ASR systems sometimes produce fluent text that is unrelated to the speech they receive. We view these hallucinations as one possible consequence of a broader grounding failure, in which the transcript is no longer adequately guided by the audio. To understand where this failure becomes possible, we study two independently trained Conformer-Large recognizers - one CTC and one RNN-T - under environmental degradation and speaker-background shift. In both models, the final encoder stage emerges as a critical boundary: bypassing the final block causes divergence on nearly every utterance, whereas bypassing middle blocks has little effect. At this same stage, the representations become more compact, text becomes readable by the trained decoder, and grapheme information becomes explicit. Importantly, the intervention produces garbled or repetitive output rather than fluent fabrication. Our result therefore identifies a mechanistic precondition for hallucination - the failure to produce adequately grounded output - not the complete origin of naturally occurring hallucinations. Together, the results reveal a consistent terminal-stage dependency for grounded recognition across two decoder families and multiple distribution shifts.

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2609.04404 [cs.CL]

(or arXiv:2609.04404v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2609.04404

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Hamees Sayed [view email] [v1] Thu, 3 Sep 2026 19:11:05 UTC (187 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled The Anatomy of an ASR Hallucination, by Hamees Sayed and 3 other authors

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

  • ASR hallucinations are viewed as a consequence of grounding failure, where the transcript is no longer adequately guided by the audio.
  • Both CTC and RNN-T Conformer-Large models show a consistent terminal-stage dependency across multiple distribution shifts.
  • Bypassing the final encoder block causes divergence on nearly every utterance, while skipping middle blocks has little effect.
  • The intervention produces garbled or repetitive output, indicating the study reveals a precondition for hallucination rather than its full origin.

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