• DOI:10.1109/TCDS.2022.3210751
• Corpus ID: 232232776

Double Articulation Analyzer with Prosody for Unsupervised Word and Phoneme Discovery

@article{Okuda2021DoubleAA,
  title={Double Articulation Analyzer with Prosody for Unsupervised Word and Phoneme Discovery},
  author={Yasuaki Okuda and Ryo Ozaki and Tadahiro Taniguchi},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.08199}
}

• Yasuaki Okuda, Ryo Ozaki, T. Taniguchi
• Published 15 March 2021
• Computer Science
• ArXiv

—Word and phoneme discovery are important tasks in language development for human infants. Infants acquire words and phonemes from unsegmented speech signals using segmen- tation cues, such as distributional, prosodic, and co-occurrence cues. Many pre-existing computational models that represent the process tend to focus on distributional or prosodic cues. This paper proposes a nonparametric Bayesian probabilistic generative model called the prosodic hierarchical Dirichlet process-hidden language model (Prosodic HDP-HLM) for simultaneous phoneme and word discovery from continuous speech signals. Prosodic HDP-HLM, an extension of HDP-HLM, considers both prosodic and distributional cues within a single integrative generative model. We propose a prosodic double articulation analyzer (Prosodic DAA) by deriving an inference procedure for Prosodic HDP-HLM. We conducted three experiments on different types of datasets, i.e., Japanese vowel sequence, utterances for teaching object names and features, and utterances following Zipf’s law and demonstrate the validity of the proposed method. The results show that the Prosodic DAA successfully uses prosodic cues and outperforms a method that solely uses distributional cues. In contrast, the phoneme discovery performance did not improve. We also show that prosodic cues contributed to word discovery performance more when the word frequency was distributed more naturally, i.e., following Zipf’s law. The main contributions of this study are as follows: