Samsone：面向端侧推理的开源小型音频语言模型系列

Electrical Engineering and Systems Science > Audio and Speech Processing arXiv:2609.21666 (eess) [Submitted on 18 Sep 2026] Title:Samsone: A Family of Open Small Audio Language Models for On-Device Inference Authors:Piotr Masztalski, Michał K. Grzeszczyk, Olaf Sikorski View a PDF of the paper titled Samsone: A Family of Open Small Audio Language Models for On-Device Inference, by Piotr Masztalski and 2 other authors View PDF HTML (experimental) Abstract:The success of Large Audio Language Models has driven the development of massive multimodal networks exceeding billions of parameters. However, the demand for privacy-preserving, low-latency processing has shifted focus toward Small Audio Language Models (SALMs) capable of on-device execution. In this paper, we introduce Samsone, a family of SALMs designed for edge computing. Our core model, Samsone-134M, establishes a new state-of-the-art for its size class across multiple benchmarks. We further explore the scaling laws of SALMs by introducing Samsone-99M and Samsone-356M. Despite their compact footprint, the Samsone family delivers performance competitive with models orders of magnitude larger. To foster open research and reproducibility, we train Samsone on publicly available data. We release the training code, model weights, mobile-optimized checkpoints and provide an open-source Android application to demonstrate real-time on-device inference of Samsone. Comments: Subjects: Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI) Cite as: arXiv:2609.21666 [eess.AS] (or arXiv:2609.21666v1 [eess.AS] for this version) https://doi.org/10.48550/arXiv.2609.21666 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Piotr Masztalski [view email] [v1] Fri, 18 Sep 2026 12:03:11 UTC (357 KB) Full-text links: Access Paper: View a PDF of the paper titled Samsone: A Family of Open Small Audio Language Models for On-Device Inference, by Piotr Masztalski and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: eess.AS new | recent | 2026-09 Change to browse by: cs cs.AI eess References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × 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? | Disable MathJax (What is MathJax?)