Exploiting end of sentences and speaker alternations in language modeling for multiparty conversations

Hiroto Ashikawa, Naohiro Tawara, Atsunori Ogawa, Tomoharu Iwata, Tetsunori Kobayashi, Tetsuji Ogawa

    研究成果: Conference contribution

    1 被引用数 (Scopus)

    抄録

    The effective handling of end-of-sentences and speaker alternations, both of which are frequently observed in multiparty conversations, in recurrent neural network language models (RNNLMs) is investigated. This kind of auxiliary information is represented as context cues and feature vectors. The former representation can be inserted directory into a transcription and treated as a word token, while the latter serves as auxiliary input to the neural networks. Experimental comparisons using multiparty conversation data, including the AMI meeting corpus, demonstrated that both representations contribute to improvement of the RNNLMs, and that dealing with the end-of-sentences is important, especially on the multiparty conversations.

    本文言語English
    ホスト出版物のタイトルProceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
    出版社Institute of Electrical and Electronics Engineers Inc.
    ページ1263-1267
    ページ数5
    2018-February
    ISBN(電子版)9781538615423
    DOI
    出版ステータスPublished - 2018 2 5
    イベント9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 - Kuala Lumpur, Malaysia
    継続期間: 2017 12 122017 12 15

    Other

    Other9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
    CountryMalaysia
    CityKuala Lumpur
    Period17/12/1217/12/15

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Human-Computer Interaction
    • Information Systems
    • Signal Processing

    フィンガープリント 「Exploiting end of sentences and speaker alternations in language modeling for multiparty conversations」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

    引用スタイル