"Yeah Right": Sarcasm Recognition for Spoken Dialogue Systems

Abstract

The robust understanding of sarcasm in a spoken dialogue system requires a reformulation of the dialogue manager's basic assumptions behind, for example, user behavior and grounding strategies. But automatically detecting a sarcastic tone of voice is not a simple matter. This paper presents some experiments toward sarcasm recognition using prosodic, spectral, and contextual cues. Our results demonstrate that spectral and contextual features can be used to detect sarcasm as well as a human annotator would, and confirm a long-held claim in the field of psychology - that prosody alone is not sufficient to discern whether a speaker is being sarcastic.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2006
Accession Number
AD1171612

Entities

People

  • David R Traum
  • Joseph Tepperman
  • Shrikanth Narayanan

Organizations

  • University of Southern California

Tags

DTIC Thesaurus Topics

  • Agreements
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Automatic
  • Coding
  • Computer Programming
  • Data Mining
  • Dialogue Systems
  • Hidden Markov Models
  • Information Science
  • Language
  • Laughter
  • Machine Learning
  • Markov Models
  • New York
  • Probability
  • Psychology
  • Recognition
  • Standards
  • Switchboards
  • Taxonomy
  • Training
  • Universities

Readers

  • Computational Linguistics
  • Speech Processing/Speech Recognition.
  • Systems Analysis and Design