SPEAKER: Sravana Reddy
University of Chicago
TITLE: Unsupervised Learning of Pronunciations
How well can we guess the sound of a word from its textual representation? Translating written language to its spoken form is a key component of speech technology. The standard problem of learning a model of letter to-phoneme transformations from an existing lexicon is especially hard in writing systems like English where there is a non-trivial mapping between letters and phonemes. The problem becomes even more complex when we involve accents and dialects, or when we have no parallel training data.
In this talk, I will present some of my research that involves learning pronunciations with various degrees of unsupervision. I will first describe two methods for learning the latent alignments between letters and phonemes from an existing pronunciation lexicon in order to build a letter-to-phoneme model. I will also present a method to augment letter-to-phoneme models with speech information -- specifically, speech recognition errors on out-of-vocabulary words. The talk will then discuss the problem of extracting rhyme and meter in an unsupervised way from written poetry, both of which provide major cues to historical and dialectical pronunciations. Finally, I will present ongoing work on learning pronunciations from speech when both the lexicon and the speech transcriptions are unknown, a novel problem that is potentially useful for low-resource languages and dialects.
This talk covers joint work with John Goldsmith, Kevin Knight, Evandro Gouvea, and Karen Livescu.
Sravana Reddy is a PhD student in Computer Science at the University of Chicago. Her research interests are primarily in unsupervised learning and phonology/pronunciation modeling, as well as general problems in natural language processing, speech, linguistics, and machine learning. John Goldsmith is Sravana's adviser, she also works with Karen Livescu at TTI Chicago and Kevin Knight at ISI.