AI & ML
Contextual Pictograms for Repairing Multilingual ASR Errors
arXiv cs.HC0 views
arXiv:2611.05637v1 Announce Type: cross Abstract: Speech transcription errors can be difficult to recognize when competing word hypotheses are unfamiliar or visually similar. We describe an interface that combines alternative transcripts, replay and contextually checked pictograms for selected uncertain concepts. The system will initially support French and Spanish functional utterances. A counterbalanced study will assess whether pictorial feedback helps listeners recover the speaker's intended action beyond text alternatives alone. We will also quantify semantic mismatch and additional interaction time, since an inappropriate image can reinforce the wrong interpretation rather than repair it.
Source:https://arxiv.org/abs/2611.05637PreviousWhose Transparency is it Anyway? Understanding Generative AI Transparency Needs and Gaps Across StakeholdersNextHow Do Artificial Agents Make Decisions in Light of Visual Data?
Related posts
Factorized MLLM Embeddings for Composed Image Retrieval
0arXiv cs.IR
Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems
0arXiv cs.IR
Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks
0arXiv cs.IR
When Is Complex Chunking Worth It? A Multi-Objective Evaluation of Chunking Methods at Scale
0arXiv cs.IR
IMFuse: Instance-Aware Multi-Layer Fusion for LLM-Enhanced Sequential Recommendation
0arXiv cs.IR
When Reviews Are Scarce: Structure-Aware Review Imputation for Recommendation in Realistic Sparse Review Settings
0arXiv cs.IR