본문 바로가기
HOME> 논문 > 논문 검색상세

논문 상세정보

Computer speech & language v.48, 2018년, pp.80 - 102   SCIE
본 등재정보는 저널의 등재정보를 참고하여 보여주는 베타서비스로 정확한 논문의 등재여부는 등재기관에 확인하시기 바랍니다.

Prediction of a hotspot pattern in keyword search results

Gao, Jie (Department of Computer Science, Columbia University, New York, NY 10027 ) ; Radeva, Axinia (Center for Computational Learning Systems, Columbia University, New York, NY 10027 ) ; Shen, Chuyao (Department of Statistics Science, Columbia University, New York, NY 10027 ) ; Wang, Shiqi (Department of Statistics Science, Columbia University, New York, NY 10027 ) ; Wang, Qianbo (Department of Statistics Science, Columbia University, New York, NY 10027 ) ; Passonneau, Rebecca J. (Corresponding author at: Department of Computer Science and Engineering, School of Electrical Engineering and Computer Science, Pennsylvania State University, 342 Information Sciences and Technology Building, University Park, PA 16802, USA. ) ;
  • 초록  

    Abstract This paper identifies and models a phenomenon observed across low-resource languages in keyword search results from speech retrieval systems where the speech recognition has high error rate, due to very limited training data. High confidence correct detections ( HCCD s) of keywords are rare, yet often succeed one another closely in time. We refer to these close sequences of HCCD s as keyword hotspots . The ability to predict keyword hotspots could support speech retrieval, and provide new insights into the behavior of speech recognition systems. We treat hotspot prediction as a binary classification task on all word-sized time intervals in an audio file of a telephone conversation, using prosodic features as predictors. Rare events that follow this pattern are often modeled as a self-exciting point process ( SEPP ), meaning the occurrence of a rare event excites a following one. To label successive points in time as occurring within a hotspot or not, we fit a SEPP function to the distribution of HCCD s in the keyword search output. Two major learning challenges are that the size of the positive class is very small, and the training and test data have dissimilar distributions. To address these challenges, we develop a novel data selection framework that chooses training data with good generalization properties. Results exhibit superior generalization performance. Highlights Hotspots of keyword search detections over speech recognition output are identified. Keyword hotspots are modeled as Hawkes process to automatically label data. Prosodic features are used to predict hotspots for word-sized time intervals. Two challenges, class imbalance and disparity of training and test data, are addressed. A novel data selection method with good generalization properties is proposed.


  • 주제어

    Self-exciting point process .   Data selection .   Keyword search .   Speech retrieval.  

 활용도 분석

  • 상세보기

    amChart 영역
  • 원문보기

    amChart 영역

원문보기

무료다운로드
  • 원문이 없습니다.
유료다운로드

유료 다운로드의 경우 해당 사이트의 정책에 따라 신규 회원가입, 로그인, 유료 구매 등이 필요할 수 있습니다. 해당 사이트에서 발생하는 귀하의 모든 정보활동은 NDSL의 서비스 정책과 무관합니다.

원문복사신청을 하시면, 일부 해외 인쇄학술지의 경우 외국학술지지원센터(FRIC)에서
무료 원문복사 서비스를 제공합니다.

NDSL에서는 해당 원문을 복사서비스하고 있습니다. 위의 원문복사신청 또는 장바구니 담기를 통하여 원문복사서비스 이용이 가능합니다.

이 논문과 함께 출판된 논문 + 더보기