Phorum

The Berkeley Phonetics and Phonology Forum ("Phorum") is a weekly talk and discussion series featuring presentations on all aspects of phonology and phonetics. 

We meet Mondays 12-1pm in 1229 Dwinelle.

Phorum is organized by Emily Grabowski and Yevgeniy Melguy. Our emails are respectively "emily_grabowski" and "ymelguy" @berkeley.edu.


Fall 2019 - Upcoming Talks

November 25

Gasper Begus (University of Washington) "Generative Adversarial Networks, phonetics, phonology, and sound change."

Applications of deep learning have recently seen exponential growth in computational cognitive science and linguistics, but the vast majority of models operate exclusively on syntactic, semantic, or symbolic levels. In this talk, I propose that phonetic and phonological learning can be modeled as a dependency between random space and data generated by the Generative Adversarial Networks (Goodfellow et al. 2014, Radford et al. 2015, Donahue et al. 2019). The advantage of this approach is that the networks are trained on raw acoustic data in a completely unsupervised manner with no pre-assumed levels of abstraction and that phonetic and phonological learning are thus modeled simultaneously. I argue that the network learns an allophonic distribution -- the distribution of aspiration in English. The learning is, however, imperfect, and the network occasionally generates innovative outputs that violate the training data, but closely resemble imperfect learning in L1 acquisition.
 
I additionally propose a method for uncovering the network's internal representations and argue that the network learns to encode phonetic and phonological information in its latent space. For example, the proposed method identifies variables in the latent space that have parallels in phonetic and phonological features; by manipulating a specific variable, we can actively force certain sounds (such as [s]) in the output and control their amplitudes and spectral properties. The talk will also discuss how the network’s architecture and innovative outputs resemble and differ from linguistic behavior in language acquisition, speech disorders, and speech errors.

Archive

A list of previous Phorum talks can be found at the Phorum Archive