Research map / Vision-language and multimodal / Human and embodied modeling
Unsupervised Learning of Spoken Language with Visual Context
David Harwath, Antonio Torralba, James Glass
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| truncate audio captions to 20 s instead of 10 s (ablation) | audio-image model · Places audio captions | recall: .056 -> .066 | Improved |
| max instead of mean pooling over audio caption (ablation) | audio-image model · Places audio captions | recall | No clear effect |
| L2-normalize only the acoustic embeddings (ablation) | audio-image model · Places audio captions | recall | Improved |
| also L2-normalize image embeddings (cosine similarity instead of dot product) (ablation) | audio-image model · Places audio captions | recall | Hurt |
| embedding dimension d = 1024 (ablation) | audio-image model · Places audio captions | recall | Improved |
| use first conv layer features versus MFCC39 baseline | audio-image model · TIMIT keyword spotting | EER: 0.127 -> 0.049 | Improved |
| compare to best prior unsupervised [12] | audio-image model · TIMIT keyword spotting | P@N: 0.63 -> 0.62 | No clear effect |
| compare to best prior unsupervised [12] | audio-image model · TIMIT keyword spotting | EER: 0.169 -> 0.049 | Improved |
Closest papers by meaning
- Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input (ECCV 2018 · similarity 0.90)
- Deep Audio-Visual Speech Recognition (TPAMI 2018 · similarity 0.87)
- Vision-Speech Models: Teaching Speech Models to Converse about Images (CVPR 2026 · similarity 0.86)
- video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models (ICML 2024 · similarity 0.86)
- Revisiting the Role of Language Priors in Vision-Language Models (ICML 2024 · similarity 0.86)
- Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
