Unsupervised Multimodal Word Discovery based on Double Articulation Analysis with Co-occurrence cues

Abstract

Human infants acquire their verbal lexicon with minimal prior knowledge of language based on the statistical properties of phonological distributions and the co-occurrence of other sensory stimuli. This study proposes a novel fully unsupervised learning method for discovering speech units using phonological information as a distributional cue and object information as a co-occurrence cue. The proposed method can acquire words and phonemes from speech signals using unsupervised learning and utilize object information based on multiple modalities-vision, tactile, and auditory-simultaneously. The proposed method is based on the nonparametric Bayesian double articulation analyzer (NPB-DAA) discovering phonemes and words from phonological features, and multimodal latent Dirichlet allocation (MLDA) categorizing multimodal information obtained from objects. In an experiment, the proposed method showed higher word discovery performance than baseline methods. Words that expressed the characteristics of objects (i.e., words corresponding to nouns and adjectives) were segmented accurately. Furthermore, we examined how learning performance is affected by differences in the importance of linguistic information. Increasing the weight of the word modality further improved performance relative to that of the fixed condition.

arXiv commentAccepted to IEEE TRANSACTIONS ON COGNITIVE DEVELOPMENTAL SYSTEMS

References in corpus (7)

• Neural Discrete Representation Learning
• Unsupervised speech representation learning using WaveNet autoencoders
• Representations of language in a model of visually grounded speech signal
• Unsupervised word segmentation and lexicon discovery using acoustic word embeddings
• Neuro-SERKET: Development of Integrative Cognitive System through the Composition of Deep Probabilistic Generative Models
• Nonparametric Bayesian Double Articulation Analyzer for Direct Language Acquisition from Continuous Speech Signals
• Unsupervised Phoneme and Word Discovery from Multiple Speakers using Double Articulation Analyzer and Neural Network with Parametric Bias

Cited by in corpus (1)

• On Parallelism in Music and Language: A Perspective from Symbol Emergence Systems based on Probabilistic Generative Models