36 citations · 42 across the 2 of their papers we have counts for
2 papers
eess.AS2019★ 6 cited
Unsupervised Phoneme and Word Discovery from Multiple Speakers using Double Articulation Analyzer and Neural Network with Parametric Bias
Ryo Nakashima, Ryo Ozaki, Tadahiro Taniguchi
This paper describes a new unsupervised machine learning method for simultaneous phoneme and word discovery from multiple speakers. Human infants can acquire knowledge of phonemes…
cs.AI2015★ 36 cited
Nonparametric Bayesian Double Articulation Analyzer for Direct Language Acquisition from Continuous Speech Signals
Tadahiro Taniguchi, Ryo Nakashima, Shogo Nagasaka
Human infants can discover words directly from unsegmented speech signals without any explicitly labeled data. In this paper, we develop a novel machine learning method called nonp…