Spoken Language Understanding without Speech Recognition

Yuan-Ping Chen; Ryan Price; Srinivas Bangalore

ICASSP 2018accepted0 citations

Spoken Language Understanding without Speech Recognition

Yuan-Ping Chen, Ryan Price, Srinivas Bangalore

Abstract

While conventional approaches to spoken language understanding involve cascading a speech recognizer with a language understanding system, in this paper, we describe a novel approach for deriving semantics directly from the speech signal without the need for an explicit speech recognition step. We evaluate this approach in the context of a customer care dialog system and demonstrate its effectiveness in comparison to the conventional approach.

BibTeX

@inproceedings{icassp2018_spokenlanguageun,
  title = {Spoken Language Understanding without Speech Recognition},
  author = {Yuan-Ping Chen and Ryan Price and Srinivas Bangalore},
  booktitle = {ICASSP 2018},
  year = {2018}
}