Nonparametric Bayesian Double Articulation Analyzer for Direct Language Acquisition from Continuous Speech Signals

no code implementations • 22 Jun 2015 • Tadahiro Taniguchi, Ryo Nakashima, Shogo Nagasaka

In this paper, we develop a novel machine learning method called nonparametric Bayesian double articulation analyzer (NPB-DAA) that can directly acquire language and acoustic models from observed continuous speech signals.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4