INTERSPEECH 2006 - ICSLP Ninth International Conference on Spoken Language Processing Pittsburgh, PA, USA September 17-21, 2006

Finding the Gaps: Applying a Connectionist Model of Word Segmentation to Noisy Phone-Recognized Speech Data

C. Anton Rytting

Ohio State University, USA

The Christiansen model of word segmentation [1] is a connectionist framework for modeling how infants combine multiple cues in learning and processing language. Most studies applying this model assume idealized input with adult-like representations of phonemes and features, with little or no degradation of the input signal. From these studies, it is difficult to tell if the model is robust to non-idealized, noisy input, which may correspond more closely to an infant languagelearner’s experience.

This study tests the robustness of the Christiansen model by providing input from a minimally-trained phone recognizer on infant-directed speech. Some degradation of performance is observed, but the model still performs above chance. This finding represents a first step in developing more realistic input representations for models of child language acquisition.

Full Paper

Bibliographic reference.  Rytting, C. Anton (2006): "Finding the gaps: applying a connectionist model of word segmentation to noisy phone-recognized speech data", In INTERSPEECH-2006, paper 2062-Tue3CaP.14.