This paper presents a new approach to language model construction, learning a language model not from text, but directly from continuous speech. A phoneme lattice is created using...
Graham Neubig, Masato Mimura, Shinsuke Mori, Tatsu...
Abstract. Two new techniques based on nonparametric estimation of probability densities are introduced which improve on the performance of equivalent robust methods currently emplo...
A central problem in artificial intelligence is to choose actions to maximize reward in a partially observable, uncertain environment. To do so, we must learn an accurate model of ...
This paper presents a video acquisition system that can learn automatic video capture from human's camera operations. Unlike a predefined camera control system, this system c...
This paper presents a method for learning a semantic parser from ambiguous supervision. Training data consists of natural language sentences annotated with multiple potential mean...