header
Local cover image
Local cover image
Image from OpenLibrary

Learning to rank for spoken content transcriptions / Farida Mohamed Sabry ; Supervised Nevin Darwish , Mayada Hadhoud

By: Contributor(s): Material type: TextTextLanguage: English Publication details: Cairo : Farida Mohamed Sabry , 2018Description: 70 P. : charts ; 30cmOther title:
  • التعلم ا{uئإئ٥}لى لتصنيف نتائج بحث المحتوى المنطوق [Added title page title]
Subject(s): Online resources: Available additional physical forms:
  • Issued also as CD
Dissertation note: Thesis (Ph.D.) - Cairo University - Faculty of Engineering - Department of Computer Engineering Summary: This thesis addresses the problem of ranking of spoken content retrieval (SCR). It shows the effectiveness of applying learning to rank techniques for the ranking of transcriptions based on features extracted from the metadata and the timed spoken content transcription with respect to one of the base- line unsupervised traditional scoring. Algorithms for reduction and bagging of features are implemented that outperform the state-of-art algorithms
Tags from this library: No tags from this library for this title. Log in to add tags.
Star ratings
    Average rating: 0.0 (0 votes)
Holdings
Item type Current library Home library Call number Copy number Status Barcode
Thesis Thesis قاعة الرسائل الجامعية - الدور الاول المكتبة المركزبة الجديدة - جامعة القاهرة Cai01.13.06.Ph.D.2018.Fa.L (Browse shelf(Opens below)) Not for loan 01010110076037000
CD - Rom CD - Rom مخـــزن الرســائل الجـــامعية - البدروم المكتبة المركزبة الجديدة - جامعة القاهرة Cai01.13.06.Ph.D.2018.Fa.L (Browse shelf(Opens below)) 76037.CD Not for loan 01020110076037000

Thesis (Ph.D.) - Cairo University - Faculty of Engineering - Department of Computer Engineering

This thesis addresses the problem of ranking of spoken content retrieval (SCR). It shows the effectiveness of applying learning to rank techniques for the ranking of transcriptions based on features extracted from the metadata and the timed spoken content transcription with respect to one of the base- line unsupervised traditional scoring. Algorithms for reduction and bagging of features are implemented that outperform the state-of-art algorithms

Issued also as CD

There are no comments on this title.

to post a comment.

Click on an image to view it in the image viewer

Local cover image