• Home
  • Search
  • Error simulation for training statistical dialogue systems
  • Cite Icon87
  • https://doi.org/10.1109/asru.2007.4430167Copy DOI Icon

Error simulation for training statistical dialogue systems

  • Jan 1, 2007
  • Jost Schatzmann +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Human-machine dialogue is heavily influenced by speech recognition and understanding errors and it is hence desirable to train and test statistical dialogue system policies under realistic noise conditions. This paper presents a novel approach to error simulation based on statistical models for word-level utterance generation, ASR confusions, and confidence score generation. While the method explicitly models the context-dependent acoustic confusability of words and allows the system specific language model and semantic decoder to be incorporated, it is computationally inexpensive and thus potentially suitable for running thousands of training simulations. Experimental evaluation results with a POMDP-based dialogue system and the Hidden Agenda User Simulator indicate a close match between the statistical properties of real and synthetic errors.

Similar Papers
  • Book Chapter
  • Citations2

An Empirical Study of Speech Recognition Errors in Human-Computer Dialogue

  • Jan 01, 2003
  • Marc Cavazza
  • Research Article
  • Citations7

Dialogue System of Controlling Robot Based on the Theory of Finite-State Automata

  • Nov 07, 2019
  • Mekhatronika, Avtomatizatsiya, Upravlenie
  • Yin Shuai +1
  • Research Article
  • Citations1

Aoba_v3 bot: a multimodal chatbot system combining rules and various response generation models

  • Aug 02, 2023
  • Advanced Robotics
  • Shoji Moriya +9
  • Conference Article
  • Citations3

Towards human-machine dialog in Slovak

  • May 01, 2016
  • Stanislav Ondas +1
  • PDF
  • Conference Article
  • Citations15

Dependency Parsing for Spoken Dialog Systems

  • Jan 01, 2019
  • Sam Davidson +2
  • PDF
  • Research Article
  • Citations9

A Survey on Surface Defect Inspection Based on Generative Models in Manufacturing

  • Aug 02, 2024
  • Applied Sciences
  • Yu He +3
  • Research Article
  • Citations16

Auditory function and speech understanding in listeners who qualify for EAS surgery.

  • Apr 01, 2007
  • Ear and hearing
  • René H Gifford +3
  • Research Article
  • Citations6

Semantic and phonetic automatic reconstruction of medical dictations

  • Jul 14, 2010
  • Computer Speech & Language
  • Stefan Petrik +8
  • Research Article

Leveraging Fluctuations of Black-Box Generative Models for Secure Deep Image Steganography

  • Mar 01, 2026
  • IEEE Transactions on Dependable and Secure Computing
  • Xiangkun Wang +4
  • PDF
  • Conference Article
  • Citations58

An Empirical Study of Self-Disclosure in Spoken Dialogue Systems

  • Jan 01, 2018
  • Abhilasha Ravichander +1
  • Conference Article
  • Citations77

Exploring ASR-free end-to-end modeling to improve spoken language understanding in a cloud-based dialog system

  • Dec 01, 2017
  • 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
  • Yao Qian +6
  • Research Article
  • Citations100

Digit Training in Noise Can Improve Cochlear Implant Users' Speech Understanding in Noise

  • Sep 01, 2011
  • Ear & Hearing
  • Sandra I Oba +2
  • Conference Article
  • Citations3

Trainbot: a spoken dialog system using partially observable Markov decision processes

  • Jan 01, 2010
  • Weidong Zhou +1
  • Research Article
  • Citations15

Human-computer interaction for virtual-real fusion

  • Jan 01, 2023
  • Journal of Image and Graphics
  • Jianhua Tao +5
  • Research Article
  • Citations33

Incidence of speech recognition errors in the emergency department

  • May 26, 2016
  • International Journal of Medical Informatics
  • Foster R Goss +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.