Using Integer Linear Programming for Detecting Speech Disfluencies

Abstract

We present a novel two-stage technique for detecting speech disfluencies based on Integer Linear Programming (ILP). In the first stage we use state-of-the-art models for speech disfluency detection, in particular, hidden-event language models, maximum entropy models and conditional random fields. During testing each model proposes possible disfluency labels which are then assessed in the presence of local and global constraints using ILP. Our experimental results show that by using ILP we can improve the performance of our models with negligible cost in processing time. The less training data is available the larger the improvement due to ILP.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2009
Accession Number
AD1160051

Entities

People

  • Kallirroi Georgila

Organizations

  • University of Southern California

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Computational Linguistics
  • Computational Science
  • Hidden Markov Models
  • Integer Programming
  • Language
  • Linear Programming
  • Linguistics
  • Machine Learning
  • Markov Models
  • Models
  • Natural Language Processing
  • Natural Languages
  • Probabilistic Models
  • Probability
  • Test Sets

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Operations Research
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Machine Translation
  • AI & ML - Neural Networks