Cem Mil Podcasts: A Spoken Portuguese Document Corpus for Multi-modal, Multi-lingual and Multi-dialect Information Access Research.

@inproceedings{garmash-2023-cem, author = {Ekaterina Garmash and Edgar Tanaka and Ann Clifton and Joana Correia and Sharmistha Jat and Winstead Zhu and Rosie Jones and Jussi Karlgren}, editor = {Avi Arampatzis and Evangelos Kanoulas and Theodora Tsikrika and Stefanos Vrochidis and Anastasia Giahanou and Dan Li and Mohammad Aliannejadi and Michail Vlachos and Guglielmo Faggioli and Nicola Ferro}, title = {{Cem Mil Podcasts: A Spoken Portuguese Document Corpus for Multi-modal, Multi-lingual and Multi-dialect Information Access Research}}, booktitle = {{Experimental IR Meets Multilinguality, Multimodality, and Interaction - 14th International Conference of the CLEF Association, CLEF 2023, Thessaloniki, Greece, September 18-21, 2023, Proceedings}}, series = {Lecture Notes in Computer Science}, volume = {14163}, pages = {48--59}, publisher = {Springer}, year = {2023}, url = {https://doi.org/10.1007/978-3-031-42448-9_5}, doi = {https://doi.org/10.1007/978-3-031-42448-9_5} }