Multiscale recurrent neural network based language model

Tsuyoshi Morioka, Tomoharu Iwata, Takaaki Hori, Tetsunori Kobayashi

    研究成果: Conference contribution

    7 被引用数 (Scopus)

    抄録

    We describe a novel recurrent neural network-based language model (RNNLM) dealing with multiple time-scales of contexts. The RNNLM is now a technical standard in language model- ing because it remembers some lengths of contexts. However, the RNNLM can only deal with a single time-scale of a con- text, regardless of the subsequent words and topic of the spo- ken utterance, even though the optimal time-scale of the con- text can vary under such conditions. In contrast, our multiscale RNNLM enables incorporating with sufficient flexibility, and it makes use of various time-scales of contexts simultaneously and with proper weights for predicting the next word. Experi- mental comparisons carried out in large vocabulary spontaneous speech recognition demonstrate that introducing the multiple time-scales of contexts into the RNNLM yielded improvements over existing RNNLMs in terms of the perplexity and word er- ror rate.

    本文言語English
    ホスト出版物のタイトルProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
    出版社International Speech and Communication Association
    ページ2366-2370
    ページ数5
    2015-January
    出版ステータスPublished - 2015
    イベント16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015 - Dresden, Germany
    継続期間: 2015 9月 62015 9月 10

    Other

    Other16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015
    国/地域Germany
    CityDresden
    Period15/9/615/9/10

    ASJC Scopus subject areas

    • 言語および言語学
    • 人間とコンピュータの相互作用
    • 信号処理
    • ソフトウェア
    • モデリングとシミュレーション

    フィンガープリント

    「Multiscale recurrent neural network based language model」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