Improving Language Models in Speech-Based Human-Machine Interaction

Improving Language Models in Speech-Based Human-Machine Interaction

This work focuses on speech-based human-machine interaction. Specifically, a Spoken Dialogue System (SDS) that could be integrated into a robot is considered. Since Automatic Speech Recognition is one of the most sensitive tasks that must be confronted in such systems, the goal of this work is to im...

Full description

Bibliographic Details
Main Authors: Raquel Justo, Oscar Saz, Antonio Miguel, M. Inés Torres, Eduardo Lleida
Format: Article
Language:English
Published: SAGE Publishing 2013-02-01
Series:International Journal of Advanced Robotic Systems
Online Access:https://doi.org/10.5772/55407
id doaj-17f8c2a5e1a849e59fc98b1829541d95
record_format Article
spelling doaj-17f8c2a5e1a849e59fc98b1829541d952020-11-25T03:15:32ZengSAGE PublishingInternational Journal of Advanced Robotic Systems1729-88142013-02-011010.5772/5540710.5772_55407Improving Language Models in Speech-Based Human-Machine InteractionRaquel Justo0Oscar Saz1Antonio Miguel2M. Inés Torres3Eduardo Lleida4 Department of Electricity and Electronics, University of the Basque Country, Leioa, Spain Language Technologies Institute of Carnegie Mellon University, Pittsburgh, PA, USA Communications Technology Group, Aragon Institute for Engineering Research, University of Zaragoza, Zaragoza, Spain Department of Electricity and Electronics, University of the Basque Country, Leioa, Spain Communications Technology Group, Aragon Institute for Engineering Research, University of Zaragoza, Zaragoza, SpainThis work focuses on speech-based human-machine interaction. Specifically, a Spoken Dialogue System (SDS) that could be integrated into a robot is considered. Since Automatic Speech Recognition is one of the most sensitive tasks that must be confronted in such systems, the goal of this work is to improve the results obtained by this specific module. In order to do so, a hierarchical Language Model (LM) is considered. Different series of experiments were carried out using the proposed models over different corpora and tasks. The results obtained show that these models provide greater accuracy in the recognition task. Additionally, the influence of the Acoustic Modelling (AM) in the improvement percentage of the Language Models has also been explored. Finally the use of hierarchical Language Models in a language understanding task has been successfully employed, as shown in an additional series of experiments.https://doi.org/10.5772/55407
collection DOAJ
language English
format Article
sources DOAJ
author Raquel Justo
Oscar Saz
Antonio Miguel
M. Inés Torres
Eduardo Lleida
spellingShingle Raquel Justo
Oscar Saz
Antonio Miguel
M. Inés Torres
Eduardo Lleida
Improving Language Models in Speech-Based Human-Machine Interaction
International Journal of Advanced Robotic Systems
author_facet Raquel Justo
Oscar Saz
Antonio Miguel
M. Inés Torres
Eduardo Lleida
author_sort Raquel Justo
title Improving Language Models in Speech-Based Human-Machine Interaction
title_short Improving Language Models in Speech-Based Human-Machine Interaction
title_full Improving Language Models in Speech-Based Human-Machine Interaction
title_fullStr Improving Language Models in Speech-Based Human-Machine Interaction
title_full_unstemmed Improving Language Models in Speech-Based Human-Machine Interaction
title_sort improving language models in speech-based human-machine interaction
publisher SAGE Publishing
series International Journal of Advanced Robotic Systems
issn 1729-8814
publishDate 2013-02-01
description This work focuses on speech-based human-machine interaction. Specifically, a Spoken Dialogue System (SDS) that could be integrated into a robot is considered. Since Automatic Speech Recognition is one of the most sensitive tasks that must be confronted in such systems, the goal of this work is to improve the results obtained by this specific module. In order to do so, a hierarchical Language Model (LM) is considered. Different series of experiments were carried out using the proposed models over different corpora and tasks. The results obtained show that these models provide greater accuracy in the recognition task. Additionally, the influence of the Acoustic Modelling (AM) in the improvement percentage of the Language Models has also been explored. Finally the use of hierarchical Language Models in a language understanding task has been successfully employed, as shown in an additional series of experiments.
url https://doi.org/10.5772/55407
work_keys_str_mv AT raqueljusto improvinglanguagemodelsinspeechbasedhumanmachineinteraction
AT oscarsaz improvinglanguagemodelsinspeechbasedhumanmachineinteraction
AT antoniomiguel improvinglanguagemodelsinspeechbasedhumanmachineinteraction
AT minestorres improvinglanguagemodelsinspeechbasedhumanmachineinteraction
AT eduardolleida improvinglanguagemodelsinspeechbasedhumanmachineinteraction
_version_ 1724639016645558272

Similar Items