UITron-Speech: Towards Automated GUI Agents Based on Speech Instructions

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Han, Wenkang, Zeng, Zhixiong, Huang, Jing, Jiang, Shu, Zheng, Liming, Yang, Longrong, Qiu, Haibo, Yao, Chang, Chen, Jingyuan, Ma, Lin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909925150556160
author Han, Wenkang
Zeng, Zhixiong
Huang, Jing
Jiang, Shu
Zheng, Liming
Yang, Longrong
Qiu, Haibo
Yao, Chang
Chen, Jingyuan
Ma, Lin
author_facet Han, Wenkang
Zeng, Zhixiong
Huang, Jing
Jiang, Shu
Zheng, Liming
Yang, Longrong
Qiu, Haibo
Yao, Chang
Chen, Jingyuan
Ma, Lin
contents Autonomous agents for Graphical User Interfaces (GUIs) are revolutionizing human-computer interaction, yet their reliance on text-based instructions imposes limitations on accessibility and convenience, particularly in hands-free scenarios. To address this issue, we propose replacing text with speech as the instruction input modality for GUI agents, and introduce UITron-Speech, which is the first end-to-end GUI agent capable of directly processing speech instructions and on-device screenshots to predict user actions. To tackle the problem of data scarcity, we synthesize high-quality speech instruction datasets using a random-speaker text-to-speech model. Additionally, we design a mixed-modality training strategy to mitigate the inherent modality imbalance in pre-trained foundation models. Furthermore, we conduct a statistical analysis of the distribution of GUI grounding prediction errors and propose a training-free two-step grounding refinement method to alleviate minor localization deviations. Extensive experiments on multiple benchmarks demonstrate that UITron-Speech achieves robust performance and superior adaptability, underscoring the feasibility and potential of speech-driven GUI agents for more accessible and intelligent human-computer interaction. Our code and datasets are available at https://github.com/UITron-hub/UITron-Speech.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11127
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UITron-Speech: Towards Automated GUI Agents Based on Speech Instructions
Han, Wenkang
Zeng, Zhixiong
Huang, Jing
Jiang, Shu
Zheng, Liming
Yang, Longrong
Qiu, Haibo
Yao, Chang
Chen, Jingyuan
Ma, Lin
Computation and Language
Artificial Intelligence
Autonomous agents for Graphical User Interfaces (GUIs) are revolutionizing human-computer interaction, yet their reliance on text-based instructions imposes limitations on accessibility and convenience, particularly in hands-free scenarios. To address this issue, we propose replacing text with speech as the instruction input modality for GUI agents, and introduce UITron-Speech, which is the first end-to-end GUI agent capable of directly processing speech instructions and on-device screenshots to predict user actions. To tackle the problem of data scarcity, we synthesize high-quality speech instruction datasets using a random-speaker text-to-speech model. Additionally, we design a mixed-modality training strategy to mitigate the inherent modality imbalance in pre-trained foundation models. Furthermore, we conduct a statistical analysis of the distribution of GUI grounding prediction errors and propose a training-free two-step grounding refinement method to alleviate minor localization deviations. Extensive experiments on multiple benchmarks demonstrate that UITron-Speech achieves robust performance and superior adaptability, underscoring the feasibility and potential of speech-driven GUI agents for more accessible and intelligent human-computer interaction. Our code and datasets are available at https://github.com/UITron-hub/UITron-Speech.
title UITron-Speech: Towards Automated GUI Agents Based on Speech Instructions
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.11127