[2606.15638] MambAdapter: Lightweight Mamba-Based Adapters for Parameter-Efficient Transfer Learning in Speech and Audio

-->

Electrical Engineering and Systems Science > Audio and Speech Processing

arXiv:2606.15638 (eess)

[Submitted on 14 Jun 2026]

Title:MambAdapter: Lightweight Mamba-Based Adapters for Parameter-Efficient Transfer Learning in Speech and Audio

Authors:Salman Hussain Ali, Umberto Cappellazzo, Mirco Ravanelli<br>View a PDF of the paper titled MambAdapter: Lightweight Mamba-Based Adapters for Parameter-Efficient Transfer Learning in Speech and Audio, by Salman Hussain Ali and Umberto Cappellazzo and Mirco Ravanelli

View PDF<br>HTML (experimental)

Abstract:Fine-tuning Transformer-based foundation models has become the dominant strategy for domain adaptation in audio and speech processing. To reduce the computational and memory costs of this process, parameter-efficient transfer learning (PETL) methods have been widely explored. Meanwhile, Mamba, a recent state-space model, has emerged as a promising alternative to Transformers for sequence modeling. In this work, we present MambAdapter, a parameter-efficient transfer learning approach that integrates Mamba into low-rank bottleneck adapters. Our design combines parameter sharing across adapters with the injection of a lightweight Mamba module, enabling more effective modeling of audio features. We demonstrate that MambAdapter matches or outperforms strong PETL baselines on four audio classification tasks and five speech recognition languages, even when operating under reduced parameter budgets.

Comments:<br>Accepted to Interspeech 2026. Code available at: this https URL

Subjects:

Audio and Speech Processing (eess.AS); Sound (cs.SD)

Cite as:<br>arXiv:2606.15638 [eess.AS]

(or<br>arXiv:2606.15638v1 [eess.AS] for this version)

https://doi.org/10.48550/arXiv.2606.15638

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Salman Sami Hussain Ali [view email]<br>[v1]<br>Sun, 14 Jun 2026 07:01:51 UTC (132 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled MambAdapter: Lightweight Mamba-Based Adapters for Parameter-Efficient Transfer Learning in Speech and Audio, by Salman Hussain Ali and Umberto Cappellazzo and Mirco Ravanelli<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

eess.AS

next >

new<br>recent<br>| 2026-06

Change to browse by:

cs<br>cs.SD<br>eess

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

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? |<br>Disable MathJax (What is MathJax?)