Learning the building blocks of speech - Sequences

 

One-line summary
Use sophisticated sequence learning techniques to learn speech like a human.

Research question:
Are segment models able to identify the building blocks of speech?

Background:
Human speech is unique in that it uses a small set of basic speech sounds and recombines them into an unlimited number of utterances. Interestingly, the basic set of speech sounds and the rules for combining them are different for every language. Humans can learn this effortlessly, but no other animal appears to be able to do this (Yip, 2006).

The proposed project is part of a larger project to understand what cognitive mechanisms have evolved to deal with learning complex speech. Part of the project consists of building learning computer models to investigate from the bottom up what mechanisms are needed to solve the problem of learning speech.

Outline of the project:

The proposed project consists of implementing two models for learning speech. The first is a Hidden Markov Model (Rabiner, 1989). This is a standard model for speech recognition, but from a cognitive point of view not a very realistic one. The second is a segment Model (Ostendorf et al., 1996)which might be a more realistic model of how humans learn speech. The aim of the project is to compare the performance of the two models on a corpus of spoken language, and to investigate in whether the representations that are learned are indeed more realistic in the segment model.

The student:

We are looking for a student who wants to do some serious programming, but who is also able to design and run an experiment with the models. As the basic questions have to do with human cognition and language, an interest in these topics is important as well.

References

Ostendorf, M., Digalakis, V. V., & Kimball, O. A. (1996). From hmm's to segment models: A unified view of stochastic modeling for speech recognition. IEEE Transactions on Speech and Audio Processing, 4(5), 360-378.

Rabiner, L. R. (1989). A tutorial on hidden markov models and selected in speech recognition. Proceedings of the IEEE, 77(2), 257–286.

Yip, M. J. (2006). The search for phonology in other species. Trends in cognitive sciences, 10(10), 442-446.

 

Please contact Bart de Boer for more information regarding this project.