Statistical Learning in Speech: A Biologically Based Predictive Learning Model

TL;DR

This paper presents a biologically plausible neural network model that learns speech patterns through predictive error-driven learning, successfully simulating infant statistical learning and word segmentation from speech data.

Contribution

It introduces a novel biologically inspired model of predictive learning that explains how statistical learning in speech can emerge from local neural mechanisms.

Findings

The model predicts in-word syllables better than next-word syllables.

It successfully simulates infant statistical learning studies.

The approach supports prediction as a basis for word segmentation.

Abstract

Infants, adults, non-human primates and non-primates all learn patterns implicitly, and they do so across modalities. The biological evidence supports the hypothesis that the mechanism for this learning is general but computationally local. We hypothesize that the mechanism itself is predictive error-driven learning. We build on recent work that advanced a biologically plausible model of error backpropagation learning which proposes that higher order thalamic nuclei provide a locale for a temporal difference between top-down predictions and an actual event outcome. Our neural network based on that work also models the auditory cortex hierarchy of core, belt and parabelt and the caudal-rostral axis within regions. We simulated two studies showing statistical learning in infants, a seminal study using synthesized speech and a more recent study using human speech. Before simulating these studies the network was trained on spoken sentences from the TIMIT corpus to emulate infant's experience listening to random speech. The implemented neural network, learning only by predicting the next brief speech segment, learned in both simulations to predict in-word syllables better than next-word syllables showing that prediction could be the basis for word segmentation and thus statistical learning.