kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
From rule-based to data-driven lexical entrainment models in spoken dialog systems
INESC-ID Lisboa, Portugal; Instituto Superior Técnico, Portugal.ORCID iD: 0000-0002-8773-9216
CMU.
INESC-ID Lisboa/Instituto Superior Técnico.
2015 (English)In: Computer speech & language (Print), ISSN 0885-2308, E-ISSN 1095-8363, Vol. 31, no 1, p. 87-112Article in journal (Refereed) Published
Abstract [en]

This paper presents uses a data-driven approach to improve Spoken Dialog System (SDS) performance by automatically finding the most appropriate terms to be used in system prompts. The literature shows that speakers use one another’s terms (entrain) when trying to create common ground during a spoken dialog. Those terms are commonly called “primes”, since they influence the interlocutors’ linguistic decision-making. This approach emulates human interaction, with a system built to propose primes to the user and accept the primes that the user proposes. These primes are chosen on the fly during the interaction, based on a set of features that indicate good candidate primes. A good candidate is one that we know is easily recognized by the speech recognizer, and is also a normal word choice given the context. The system is trained to follow the user’s choice of prime if system performance is not negatively affected. When system performance is affected, the system proposes a new prime. In our previous work we have shown how we can identify the prime candidates and how the system can select primes using rules. In this paper we go further, presenting a data-driven method to perform the same task. Live tests with this method show that use of on-the-fly entrainment reduces out-of-vocabulary and word error rate, and also increases the number of correctly transferred concepts.

Place, publisher, year, edition, pages
Academic Press, 2015. Vol. 31, no 1, p. 87-112
Keywords [en]
Lexical entrainment; Spoken dialog systems; Data-driven model; Rule-based model
National Category
Computer Sciences
Research subject
Human-computer Interaction; Information and Communication Technology
Identifiers
URN: urn:nbn:se:kth:diva-186102DOI: 10.1016/j.csl.2014.11.007ISI: 000348959100005Scopus ID: 2-s2.0-84919924844OAI: oai:DiVA.org:kth-186102DiVA, id: diva2:925388
Note

QC 20160503

Available from: 2016-05-02 Created: 2016-05-02 Last updated: 2022-06-22Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopushttp://www.sciencedirect.com/science/article/pii/S0885230814001247

Authority records

Lopes, José

Search in DiVA

By author/editor
Lopes, José
In the same journal
Computer speech & language (Print)
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 103 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf