Vela adapts an audio MLLM into a universal text-audio embedding model using 'in one word' prompts, in-context examples, and text-only contrastive training, outperforming CLAP-style models on retrieval benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval
Vela adapts an audio MLLM into a universal text-audio embedding model using 'in one word' prompts, in-context examples, and text-only contrastive training, outperforming CLAP-style models on retrieval benchmarks.