Dataset Groups Activity Stream Matching Latent Encoding for Audio-Text based Keyword Spotting The proposed end-to-end model architecture for flexible keyword spotting, consisting of encoder, projector, and audio-text aligner modules. BibTex: @dataset{Kumari_Nishu_and_Minsik_Cho_and_Devang_Naik_2024, abstract = {The proposed end-to-end model architecture for flexible keyword spotting, consisting of encoder, projector, and audio-text aligner modules.}, author = {Kumari Nishu and Minsik Cho and Devang Naik}, doi = {10.57702/46jr1588}, institution = {No Organization}, keyword = {'Audio-Text based Keyword Spotting', 'Dynamic Sequence Partitioning', 'Flexible Keyword Spotting'}, month = {dec}, publisher = {TIB}, title = {Matching Latent Encoding for Audio-Text based Keyword Spotting}, url = {https://service.tib.eu/ldmservice/dataset/matching-latent-encoding-for-audio-text-based-keyword-spotting}, year = {2024} }