Change search
ReferencesLink to record
Permanent link

Direct link
Detecting Repetitions in Spoken Dialogue Systems Using Phonetic Distances
KTH, School of Computer Science and Communication (CSC), Speech, Music and Hearing, TMH.ORCID iD: 0000-0002-8773-9216
KTH, School of Computer Science and Communication (CSC), Speech, Music and Hearing, TMH, Speech Communication and Technology.ORCID iD: 0000-0002-3323-5311
KTH, School of Computer Science and Communication (CSC), Speech, Music and Hearing, TMH, Speech Communication and Technology.ORCID iD: 0000-0002-8579-1790
Show others and affiliations
2015 (English)In: INTERSPEECH-2015, 2015, 1805-1809 p.Conference paper (Refereed)
Abstract [en]

Repetitions in Spoken Dialogue Systems can be a symptom of problematic communication. Such repetitions are often due to speech recognition errors, which in turn makes it harder to use the output of the speech recognizer to detect repetitions. In this paper, we combine the alignment score obtained using phonetic distances with dialogue-related features to improve repetition detection. To evaluate the method proposed we compare several alignment techniques from edit distance to DTW-based distance, previously used in Spoken-Term detection tasks. We also compare two different methods to compute the phonetic distance: the first one using the phoneme sequence, and the second one using the distance between the phone posterior vectors. Two different datasets were used in this evaluation: a bus-schedule information system (in English) and a call routing system (in Swedish). The results show that approaches using phoneme distances over-perform approaches using Levenshtein distances between ASR outputs for repetition detection.

Place, publisher, year, edition, pages
2015. 1805-1809 p.
National Category
Computer Science Language Technology (Computational Linguistics)
Identifiers
URN: urn:nbn:se:kth:diva-180405ScopusID: 2-s2.0-84959138120OAI: oai:DiVA.org:kth-180405DiVA: diva2:893732
Conference
INTERSPEECH-2015, Dresden, Germany
Note

QC 20160216

Available from: 2016-01-13 Created: 2016-01-13 Last updated: 2016-02-16Bibliographically approved

Open Access in DiVA

No full text

Scopus

Search in DiVA

By author/editor
David Lopes, JoséSalvi, GiampieroSkantze, GabrielGustafson, JoakimMeena, Raveesh
By organisation
Speech, Music and Hearing, TMHSpeech Communication and Technology
Computer ScienceLanguage Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 132 hits
ReferencesLink to record
Permanent link

Direct link