TECHNOLOGIES AND MODELS OF EARLY LANGUAGE ACQUISITION

We summarize the accomplishments of a multi-disciplinary work-shop exploring the computational and scientific issues surrounding zero resource (unsupervised) speech technologies and related mod-els of early language acquisition. Centered around the tasks of pho-netic and lexical discovery, we consider unified evaluation metrics, present two new approaches for improving speaker independence in the absence of supervision, and evaluate the application of Bayesian word segmentation algorithms to automatic subword unit tokeniza-tions. Finally, we present two strategies for integrating zero resource techniques into supervised settings, demonstrating the potential of unsupervised methods to improve mainstream technologies. Index Terms — zero resource, speech recognition, language ac-quisition, Bayesian word segmentation, speaker independence 1