AI News HubLIVE
Original source2 min read

Speech2Grasp: Data-Efficient Transfer of Text-Conditioned Grasp Detection to Speech in Humanoid Robots

This paper introduces Speech2Grasp, a framework that efficiently transfers text-conditioned models like ALBEF to speech input using a lightweight MLP projector, maintaining semantic discrimination and robustness. Real-world humanoid robot experiments show that Speech2Grasp outperforms cascaded ASR pipelines while reducing inference latency, offering a practical paradigm for extending text-conditioned systems to speech.

SourcearXiv RoboticsAuthor: Hung Nguyen, Kim Nhat Minh Nguyen, Van Duc Vu, Van-Danh Le, Hoang Huy Le, Dinh Tuan Nguyen, Pham Tuyen Le, Van-Truong Nguyen, Quan Nguyen

-->

[Submitted on 29 Jul 2026]

Title:Speech2Grasp: Data-Efficient Transfer of Text-Conditioned Grasp Detection to Speech in Humanoid Robots

View a PDF of the paper titled Speech2Grasp: Data-Efficient Transfer of Text-Conditioned Grasp Detection to Speech in Humanoid Robots, by Hung Nguyen and 8 other authors

View PDF

Abstract:Humanoid robots increasingly require multi-modal understanding for natural interaction with humans. Despite the prominence of vision-language models, they generally assume textual rather than the more natural speech inputs. In this paper, we investigate whether a well-established text-conditioned model can be transferred to speech in a data-efficient manner. Using ALBEF as a case study, we conduct diagnostic analyses showing that a lightweight MLP-based projector effectively adapts it to speech, while preserving semantic discrimination and robustness. Motivated by these findings, we introduce Speech2Grasp, a framework for data-efficient transfer of text-conditioned grasp detection to speech. Real-world humanoid robot experiments show that Speech2Grasp outperforms cascaded ASR-based pipeline, while reducing inference latency. Our findings suggest a practical paradigm for extending established text-conditioned systems to speech.

Subjects:

Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2607.26567 [cs.RO]

(or arXiv:2607.26567v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2607.26567

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Hung Nguyen [view email] [v1] Wed, 29 Jul 2026 07:40:00 UTC (5,292 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Speech2Grasp: Data-Efficient Transfer of Text-Conditioned Grasp Detection to Speech in Humanoid Robots, by Hung Nguyen and 8 other authors

View PDF

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-07

Change to browse by:

cs cs.CV

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?)