Three cheers to
Naomi Feldman, whose
Modeling the Development of Phonetic Representations has just won 3 years of NSF support. This grant is paired with one from the UK's Economic and Social Research Council to
Sharon Goldwater at Edinburgh, under the
SBE-RCUK lead agency agreement. The proposed research tests the hypothesis that children's processing of speech can become specialized for their native language through a process of dimension learning that does not rely on knowledge of sound categories. Two dimension learning models are proposed, drawing on representation learning methods that have performed well in low-resource automatic speech recognition, where extensive labeled training data are not available. The first relies on temporal information as a proxy for sound category knowledge, while the second relies on top-down information from similar words, which infants have been shown to use. Each model is trained on speech recordings from a particular language and is evaluated on its ability to predict how adults and infants with that language background discriminate sounds. The research will yield new methods for training and testing cognitive models of language with naturalistic speech recordings and has the potential to significantly impact theories of how and when children learn about the sounds of their native language.
