Dataset Groups Activity Stream SoundSpaces-Speech The SoundSpaces-Speech dataset is a benchmark for visual acoustic matching. BibTex: @dataset{Kamal_Singh_2024, abstract = {The SoundSpaces-Speech dataset is a benchmark for visual acoustic matching.}, author = {Kamal Singh}, doi = {10.57702/jqq644mq}, institution = {No Organization}, keyword = {'SoundSpaces-Speech', 'Visual Acoustic Matching'}, month = {dec}, publisher = {TIB}, title = {SoundSpaces-Speech}, url = {https://service.tib.eu/ldmservice/dataset/soundspaces-speech}, year = {2024} }
