Cross modal audio search and retrieval with joint embeddings based on text and audio

B Elizalde, S Zarar, B Raj - ICASSP 2019-2019 IEEE …, 2019 - ieeexplore.ieee.org
Existing audio search engines use one of two approaches: matching text-text or audio-audio
pairs. In the former, text queries are matched to semantically similar words in an index of …

[PDF][PDF] CROSS MODAL AUDIO SEARCH AND RETRIEVAL WITH JOINT EMBEDDINGS BASED ON TEXT AND AUDIO

B Elizalde, S Zarar, B Raj - scholar.archive.org
Existing audio search engines use one of two approaches: matching text-text or audio-audio
pairs. In the former, text queries are matched to semantically similar words in an index of …