Response Obligation Estimation That Considers Users' Repetitive Utterances using Knowledge-Guided Random Forest

Kotaro Funakoshi*, Ryota Yamagami, Shigeki Sugano, Mikio Nakano

*この研究の対応する著者

研究成果: Conference contribution

抄録

Response obligation is whether a spoken dialogue system should react to an input sound. This paper focuses on the false negative errors in response obligation estimation (ROE) that are displayed as the system's neglect of its users. When the users repeat after the system ignores their speech, ROE will likely fail again because the repeated input is similar to the previous input. Therefore, we propose an improved ROE method that considers users' repetitions. First, we show that a simple concatenation of ROE and repetition features is better than two other integration architectures. Then, we propose a modified random forest algorithm that incorporates human domain knowledge. The effectiveness is demonstrated with simulated repetitions as a 7.6-point gain from the baseline.

本文言語English
ホスト出版物のタイトル2019 IEEE-RAS 19th International Conference on Humanoid Robots, Humanoids 2019
出版社IEEE Computer Society
ページ99-105
ページ数7
ISBN(電子版)9781538676301
DOI
出版ステータスPublished - 2019 10
イベント19th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2019 - Toronto, Canada
継続期間: 2019 10 152019 10 17

出版物シリーズ

名前IEEE-RAS International Conference on Humanoid Robots
2019-October
ISSN(印刷版)2164-0572
ISSN(電子版)2164-0580

Conference

Conference19th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2019
国/地域Canada
CityToronto
Period19/10/1519/10/17

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ ビジョンおよびパターン認識
  • ハードウェアとアーキテクチャ
  • 人間とコンピュータの相互作用
  • 電子工学および電気工学

フィンガープリント

「Response Obligation Estimation That Considers Users' Repetitive Utterances using Knowledge-Guided Random Forest」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