{"language":[{"iso":"eng"}],"date_updated":"2022-01-06T06:51:12Z","type":"report","user_id":"44006","_id":"11926","status":"public","citation":{"ama":"Walter O, Schmalenstroeer J, Haeb-Umbach R. <i>A Novel Initialization Method for Unsupervised Learning of Acoustic Patterns in Speech (FGNT-2013-01)</i>.; 2013.","apa":"Walter, O., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2013). <i>A Novel Initialization Method for Unsupervised Learning of Acoustic Patterns in Speech (FGNT-2013-01)</i>.","mla":"Walter, Oliver, et al. <i>A Novel Initialization Method for Unsupervised Learning of Acoustic Patterns in Speech (FGNT-2013-01)</i>. 2013.","bibtex":"@book{Walter_Schmalenstroeer_Haeb-Umbach_2013, title={A Novel Initialization Method for Unsupervised Learning of Acoustic Patterns in Speech (FGNT-2013-01)}, author={Walter, Oliver and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2013} }","chicago":"Walter, Oliver, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. <i>A Novel Initialization Method for Unsupervised Learning of Acoustic Patterns in Speech (FGNT-2013-01)</i>, 2013.","short":"O. Walter, J. Schmalenstroeer, R. Haeb-Umbach, A Novel Initialization Method for Unsupervised Learning of Acoustic Patterns in Speech (FGNT-2013-01), 2013.","ieee":"O. Walter, J. Schmalenstroeer, and R. Haeb-Umbach, <i>A Novel Initialization Method for Unsupervised Learning of Acoustic Patterns in Speech (FGNT-2013-01)</i>. 2013."},"author":[{"first_name":"Oliver","last_name":"Walter","full_name":"Walter, Oliver"},{"last_name":"Schmalenstroeer","id":"460","first_name":"Joerg","full_name":"Schmalenstroeer, Joerg"},{"full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","id":"242","first_name":"Reinhold"}],"abstract":[{"text":"In this paper we present a novel initialization method for unsupervised learning of acoustic patterns in recordings of continuous speech. The pattern discovery task is solved by dynamic time warping whose performance we improve by a smart starting point selection. This enables a more accurate discovery of patterns compared to conventional approaches. After graph-based clustering the patterns are employed for training hidden Markov models for an unsupervised speech acquisition. By iterating between model training and decoding in an EM-like framework the word accuracy is continuously improved. On the TIDIGITS corpus we achieve a word error rate of about 13 percent by the proposed unsupervised pattern discovery approach, which neither assumes knowledge of the acoustic units nor of the labels of the training data.","lang":"eng"}],"main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2013/WaScHa2013.pdf"}],"department":[{"_id":"54"}],"oa":"1","title":"A Novel Initialization Method for Unsupervised Learning of Acoustic Patterns in Speech (FGNT-2013-01)","date_created":"2019-07-12T05:30:55Z","year":"2013"}