# Unpaired Image-to-Speech Synthesis with Multimodal Information Bottleneck

arXiv: https://arxiv.org/abs/1908.07094 · HTML: https://mlsanity.com/paper/1908.07094/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2019.

## Built on by (most cited first, 15 of 15)

- [Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval](https://mlsanity.com/paper/2112.04446/) (2021)
- [Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification](https://mlsanity.com/paper/2104.02862/) (2021)
- [Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations](https://mlsanity.com/paper/2210.17444/) (2022)
- [Preserving Modality Structure Improves Multi-Modal Learning](https://mlsanity.com/paper/2308.13077/) (2023)
- [A Survey on Integrated Sensing, Communication, and Computation](https://mlsanity.com/paper/2408.08074/) (2024)
- [Towards Modality Generalization: A Benchmark and Prospective Analysis](https://mlsanity.com/paper/2412.18277/) (2024)
- [Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue](https://mlsanity.com/paper/2106.15550/) (2021)
- [MMBind: Unleashing the Potential of Distributed and Heterogeneous Data for Multimodal Learning in IoT](https://mlsanity.com/paper/2411.12126/) (2024)
- [LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation](https://mlsanity.com/paper/2112.13985/) (2021)
- [Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2505.15217/) (2025)
- [Learning Shared Representations from Unpaired Data](https://mlsanity.com/paper/2505.21524/) (2025)
- [Variational Distillation for Multi-View Learning](https://mlsanity.com/paper/2206.09548/) (2022)
- [SVGraph: Learning Semantic Graphs from Instructional Videos](https://mlsanity.com/paper/2207.08001/) (2022)
- [Towards Unsupervised Speech Recognition at the Syllable-Level](https://mlsanity.com/paper/2510.03639/) (2025)
- [Multi-modal Bayesian Neural Network Surrogates with Conjugate Last-Layer Estimation](https://mlsanity.com/paper/2509.21711/) (2025)

## Abstract (arXiv)

Deep generative models have led to significant advances in cross-modal generation such as text-to-image synthesis. Training these models typically requires paired data with direct correspondence between modalities. We introduce the novel problem of translating instances from one modality to another without paired data by leveraging an intermediate modality shared by the two other modalities. To demonstrate this, we take the problem of translating images to speech. In this case, one could leverage disjoint datasets with one shared modality, e.g., image-text pairs and text-speech pairs, with text as the shared modality. We call this problem "skip-modal generation" because the shared modality is skipped during the generation process. We propose a multimodal information bottleneck approach that learns the correspondence between modalities from unpaired data (image and speech) by leveraging the shared modality (text). We address fundamental challenges of skip-modal generation: 1) learning multimodal representations using a single model, 2) bridging the domain gap between two unrelated datasets, and 3) learning the correspondence between modalities from unpaired data. We show qualitative results on image-to-speech synthesis; this is the first time such results have been reported in the literature. We also show that our approach improves performance on traditional cross-modal generation, suggesting that it improves data efficiency in solving individual tasks.