From Unsegmented Speech to Lexical Categories Using Phoneme Distributions
From Unsegmented Speech to Lexical Categories Using Phoneme Distributions
en-de
en-es
en-fr
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
Advantages of Computational Modeling of Language - Mediates between theory and data: evaluation, exploration, existence proofs; Requires making underlying assumptions explicit: can illuminate complex relationships between variables not easily grasped intuitively; make behaviorally testable predictions; No human subjects approval required!