Dataset Groups Activity Stream Libri-Light The dataset used in the paper is the Libri-Light dataset, which is a subset of the LibriSpeech dataset. The authors used this dataset to pre-train their proposed dual-mode ASR model. BibTex: @dataset{Sang-Gil_Lee_and_Heeseung_Kim_and_Chaehun_Shin_and_Xu_Tan_and_Chang_Liu_and_Qi_Meng_and_Tao_Qin_and_Wei_Chen_and_Sungroh_Yoon_2024, abstract = {The dataset used in the paper is the Libri-Light dataset, which is a subset of the LibriSpeech dataset. The authors used this dataset to pre-train their proposed dual-mode ASR model.}, author = {Sang-Gil Lee and Heeseung Kim and Chaehun Shin and Xu Tan and Chang Liu and Qi Meng and Tao Qin and Wei Chen and Sungroh Yoon}, doi = {10.57702/r1l8l07l}, institution = {No Organization}, keyword = {'ASR', 'Libri-Light', 'Limited or no supervision', 'Small-scale corpus', 'Speech Recognition', 'Speech recognition', 'audiobooks', 'unlabeled speech'}, month = {dec}, publisher = {TIB}, title = {Libri-Light}, url = {https://service.tib.eu/ldmservice/dataset/libri-light}, year = {2024} }
