Skip to content
AI News HubLIVE
Original source2 min read

What Do Multilingual Self-Supervised Speech Encoders Know About Sentence Meaning?

Summary

An EACL 2027 paper probes sentence-level semantics in massively multilingual self-supervised speech models across 76 languages. It finds that sentence meaning is linearly accessible from frozen speech representations but highly uneven across languages and resource tiers; cross-lingual probes can match language-specific probes on unseen languages, yet per-model monolingual decodability does not predict transfer. Scaling OmniASR wav2vec from 300M to 7B disproportionately benefits high-resource languages, and ASR tuning improves semantic decodability while making representations more language-specific. Semantic content is also entangled with acoustics, inflating performance on single-speaker corpora.

SourcearXiv Computational LinguisticsAuthor: Kevin Krahn, Eric Fosler-Lussier
What Do Multilingual Self-Supervised Speech Encoders Know About Sentence Meaning?
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 13 Nov 2026]

Title:What Do Multilingual Self-Supervised Speech Encoders Know About Sentence Meaning?

View a PDF of the paper titled What Do Multilingual Self-Supervised Speech Encoders Know About Sentence Meaning?, by Kevin Krahn and 1 other authors

View PDF HTML (experimental)

Abstract:Self-supervised speech models (S3Ms) have been scaled up to thousands of languages and millions of hours of audio, yet little is known about how these models structure semantic knowledge across languages. In this work, we probe sentence-level semantics in massively multilingual S3Ms across 76 languages, using linear maps from frozen speech representations into a frozen text embedding space, evaluated by cross-modal retrieval. Sentence meaning is linearly accessible but highly uneven across languages and resource tiers. Cross-lingual probes can match language-specific probes on languages never seen in probe training, but per-model monolingual decodability does not predict transfer. Within the OmniASR wav2vec family, scaling from 300M--7B disproportionately benefits high-resource languages, and ASR tuning sharply improves semantic decodability while making representations more language-specific. However, semantic content is entangled with acoustics, inflating apparent performance on single-speaker corpora.

Comments: Accepted to EACL 2027

Subjects:

Computation and Language (cs.CL)

ACM classes: I.2.7

Cite as: arXiv:2611.17686 [cs.CL]

(or arXiv:2611.17686v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2611.17686

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Kevin Krahn [view email] [v1] Fri, 13 Nov 2026 03:12:40 UTC (362 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled What Do Multilingual Self-Supervised Speech Encoders Know About Sentence Meaning?, by Kevin Krahn and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CL

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

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

  • Sentence-level semantics are probed across 76 languages; meaning is linearly accessible but highly uneven across languages and resource tiers.
  • Cross-lingual probes can match language-specific probes on languages never seen in probe training, but monolingual decodability does not predict transfer.
  • Scaling from 300M to 7B disproportionately benefits high-resource languages; ASR tuning boosts semantic decodability but increases language specificity.
  • Semantic content is entangled with acoustics, inflating apparent performance on single-speaker corpora.

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