# SViQA: A Unified Speech-Vision Multimodal Model for Textless Visual Question Answering

arXiv: https://arxiv.org/abs/2504.01049 · HTML: https://mlsanity.com/paper/2504.01049/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [Wav2CLIP: Learning Robust Audio Representations From CLIP](https://mlsanity.com/paper/2110.11499/) (2021)
- [VITA: Towards Open-Source Interactive Omni Multimodal LLM](https://mlsanity.com/paper/2408.05211/) (2024)
- [TinyLLaVA: A Framework of Small-scale Large Multimodal Models](https://mlsanity.com/paper/2402.14289/) (2024)
- [Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities](https://mlsanity.com/paper/2410.11190/) (2024)
- [AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs](https://mlsanity.com/paper/2311.06753/) (2023)
- [LLaSM: Large Language and Speech Model](https://mlsanity.com/paper/2308.15930/) (2023)
- [UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All](https://mlsanity.com/paper/2403.12532/) (2024)
- [Improving Multimodal Speech Recognition by Data Augmentation and Speech Representations](https://mlsanity.com/paper/2204.13206/) (2022)
- [Speech-Based Visual Question Answering](https://mlsanity.com/paper/1705.00464/) (2017)
- [S2IGAN: Speech-to-Image Generation via Adversarial Learning](https://mlsanity.com/paper/2005.06968/) (2020)

## Abstract (arXiv)

Multimodal models integrating speech and vision hold significant potential for advancing human-computer interaction, particularly in Speech-Based Visual Question Answering (SBVQA) where spoken questions about images require direct audio-visual understanding. Existing approaches predominantly focus on text-visual integration, leaving speech-visual modality gaps underexplored due to their inherent heterogeneity. To this end, we introduce SViQA, a unified speech-vision model that directly processes spoken questions without text transcription. Building upon the LLaVA architecture, our framework bridges auditory and visual modalities through two key innovations: (1) end-to-end speech feature extraction eliminating intermediate text conversion, and (2) cross-modal alignment optimization enabling effective fusion of speech signals with visual content. Extensive experimental results on the SBVQA benchmark demonstrate the proposed SViQA's state-of-the-art performance, achieving 75.62% accuracy, and competitive multimodal generalization. Leveraging speech-text mixed input boosts performance to 78.85%, a 3.23% improvement over pure speech input, highlighting SViQA's enhanced robustness and effective cross-modal attention alignment.