Seeing What You Say: Expressive Image Generation From Speech

Abstract

This paper proposes VoxStudio, the first unified and end-to-end speech-to-image model that generates expressive images directly from spoken descriptions by jointly aligning linguistic and paralinguistic information. At its core is a speech information bottleneck (SIB) module, which compresses raw speech into compact semantic tokens, preserving prosody and emotional nuance. By operating directly on these tokens, VoxStudio eliminates the need for an additional speech-to-text system, which often ignores the hidden details beyond text, e.g., tone or emotion. We also release VoxEmoset, a large-scale paired emotional speech-image dataset built via an advanced TTS engine to affordably generate richly expressive utterances. Comprehensive experiments on the SpokenCOCO, Flickr8kAudio, and VoxEmoset benchmarks demonstrate the feasibility of our method and highlight key challenges, including emotional consistency and linguistic ambiguity, paving the way for future research.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylee2025seeing

Related papers

• Facespeak: Expressive And High-quality Speech Synthesis From Human Portraits Of Different Styles (2025)0.00
• Speech Driven Talking Face Generation From A Single Image And An Emotion Condition (2020)0.00
• Emogene: Audio-driven Emotional 3D Talking-head Generation (2024)2.26
• Show And Speak: Directly Synthesize Spoken Description Of Images (2020)5.24
• Emospeech: A Corpus Of Emotionally Rich And Contextually Detailed Speech Annotations (2024)0.00
• A Methodology For Controlling The Emotional Expressiveness In Synthetic Speech -- A Deep Learning Approach (2019)5.84
• Text-free Image-to-speech Synthesis Using Learned Segmental Units (2020)10.85
• Msemotts: Multi-scale Emotion Transfer, Prediction, And Control For Emotional Speech Synthesis (2022)13.97