@inproceedings{SahaNayakBaumann, author = {Saha, Debjoy and Nayak, Shravan and Baumann, Timo}, title = {Merkel Podcast Corpus: A Multimodal Dataset Compiled from 16 Years of Angela Merkel's Weekly Video Podcasts}, series = {Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), Marseille, 20-25 June 2022}, booktitle = {Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), Marseille, 20-25 June 2022}, organization = {European Language Resources Association (ELRA)}, pages = {2536 -- 2540}, abstract = {We introduce the Merkel Podcast Corpus, an audio-visual-text corpus in German collected from 16 years of (almost) weekly Internet podcasts of former German chancellor Angela Merkel. To the best of our knowledge, this is the first single speaker corpus in the German language consisting of audio, visual and text modalities of comparable size and temporal extent. We describe the methods used with which we have collected and edited the data which involves downloading the videos, transcripts and other metadata, forced alignment, performing active speaker recognition and face detection to finally curate the single speaker dataset consisting of utterances spoken by Angela Merkel. The proposed pipeline is general and can be used to curate other datasets of similar nature, such as talk show contents. Through various statistical analyses and applications of the dataset in talking face generation and TTS, we show the utility of the dataset. We argue that it is a valuable contribution to the research community, in particular, due to its realistic and challenging material at the boundary between prepared and spontaneous speech. Accepted at LREC 2022}, language = {en} }