--- res: bibo_abstract: - 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.@eng bibo_authorlist: - foaf_Person: foaf_givenName: Oliver foaf_name: Walter, Oliver foaf_surname: Walter - foaf_Person: foaf_givenName: Joerg foaf_name: Schmalenstroeer, Joerg foaf_surname: Schmalenstroeer foaf_workInfoHomepage: http://www.librecat.org/personId=460 - foaf_Person: foaf_givenName: Reinhold foaf_name: Haeb-Umbach, Reinhold foaf_surname: Haeb-Umbach foaf_workInfoHomepage: http://www.librecat.org/personId=242 dct_date: 2013^xs_gYear dct_language: eng dct_title: A Novel Initialization Method for Unsupervised Learning of Acoustic Patterns in Speech (FGNT-2013-01)@ ...