Abstract-- Traditional methods of spoken utterance classification (SUC) adopt two independently trained phases. In the first phase, an automatic speech recognition (ASR) module ret...
Sibel Yaman, Li Deng, Dong Yu, Ye-Yi Wang, Alex Ac...
The goal of my research is to understand speech input in a continuous manner by treating the input stream as fragmental utterances. This allows us to use various approaches to pre...
Spoken language generation for dialogue systems requires a dictionary of mappings between semantic representations of concepts the system wants to express and realizations of thos...
Ryuichiro Higashinaka, Rashmi Prasad, Marilyn A. W...
An ultimate goal of AI is to build end-to-end systems that interpret natural language, reason over the resulting logical forms, and perform actions based on that reasoning. This r...