Exploring textual and speech information in dialogue act classification with speaker domain adaptation

Xuanli He, Quan Hung Tran, William Havard, Laurent Besacier, Ingrid Zukerman, Reza Haffari

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review


In spite of the recent success of Dialogue Act (DA) classification, the majority of prior works focus on text-based classification with oracle transcriptions, i.e. human transcriptions, instead of Automatic Speech Recognition (ASR)’s transcriptions. Moreover, the performance of this classification task, because of speaker domain shift, may deteriorate. In this paper, we explore the effectiveness of using both acoustic and textual signals, either oracle or ASR transcriptions, and investigate speaker domain adaptation for DA classification. Our multimodal model proves to be superior to the unimodal models, particularly when the oracle transcriptions are not available. We also propose an effective method for speaker domain adaptation, which achieves competitive results.
Original languageEnglish
Title of host publicationAustralasian Language Technology Association Workshop 2018 - Proceedings of the Workshop
Subtitle of host publication10–12 December 2018 The University of Otago Dunedin, New Zealand
EditorsSunghwan Mac Kim, Xiuzhen (Jenny) Zhang
Place of PublicationAustralia
PublisherAustralian Language Technology Association (ALTA)
Number of pages5
Publication statusPublished - 2018
EventAustralasian Language Technology Association Workshop 2018 - University of Otago, Dunedin, New Zealand
Duration: 10 Dec 201812 Dec 2018
Conference number: 16th
https://www.aclweb.org/anthology/events/alta-2018/ (Proceedings)


ConferenceAustralasian Language Technology Association Workshop 2018
Abbreviated titleALTAW 2018
CountryNew Zealand
Internet address


  • Dialogue acts
  • Domain adaptation
  • Multimodal model

Cite this