Thomas Schatz

TL;DR: The Interspeech 2015 Zero Resource Speech Challenge aims at discovering subword and word units from raw speech The challenge provides the first unified and open source suite of evaluation metrics and data sets to compare and analyse the results of unsupervised linguistic unit discovery algorithms as discussed by the authors.

TL;DR: A new framework for the evaluation of speech rep- resentations in zero-resource settings is presented, that extends and complements previous work by Carlin, Jansen and Hermansky and applies it to de- compose the standard signal processing pipelines for computing PLP and MFC coefficients.

TL;DR: In this article, the authors summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding zero resource speech technologies and related models of early language acquisition and present two strategies for integrating zero resource techniques into supervised settings, demonstrating the potential of unsupervised methods to improve mainstream technologies.

TL;DR: A comprehensive examination of sound contrasts in a large corpus of recorded, spontaneous Japanese speech demonstrates that there is a small but significant tendency for contrasts in infant-directed Speech to be less clear than those in adult-directed speech, and suggests that theories of infants’ language acquisition must posit an ability to learn from noisy data.

TL;DR: It is shown that it is possible to learn an efficient acoustic model using only a small amount of easily available word-level similarity annotations, and the resulting model is shown to perform much better than raw speech features in an ABX minimal-pair discrimination task.