A SEGMENT-LEVEL CONFIDENCE MEASURE FOR SPOKEN DOCUMENT RETRIEVAL - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

A SEGMENT-LEVEL CONFIDENCE MEASURE FOR SPOKEN DOCUMENT RETRIEVAL

Résumé

This paper presents a semantic confidence measure that aims to predict the relevance of automatic transcripts for a task of Spoken Document Retrieval (SDR). The proposed predicting method relies on the combination of Automatic Speech Recognition (ASR) confidence measure and a Semantic Com-pacity Index (SCI), that estimates the relevance of the words considering the semantic context in which they occurred. Experiments are conducted on the French Broadcast news corpus ESTER, by simulating a classical SDR usage scenario : users submit text-queries to a search engine that is expected to return the most relevant documents regarding the query. Results demonstrate the interest of using semantic level information to predict the transcription indexability.
Fichier principal
Vignette du fichier
Senay_ICASSP_2011.pdf (155.9 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00959164 , version 1 (09-11-2017)

Identifiants

  • HAL Id : hal-00959164 , version 1

Citer

Gregory Senay, Georges Linares, Benjamin Lecouteux. A SEGMENT-LEVEL CONFIDENCE MEASURE FOR SPOKEN DOCUMENT RETRIEVAL. ICASSP 2011, 2011, Prague, Czech Republic. ⟨hal-00959164⟩
152 Consultations
113 Téléchargements

Partager

Gmail Facebook X LinkedIn More