Information Retrieval from Unsegmented Broadcast News Audio

Sue E Johnson , Pierre Jourlin (1) , Karen Jones (2) , Philip C Woodland

1 LIA - Laboratoire Informatique d'Avignon
2 CEM Centre

This paper describes a system for retrieving relevant portions of broadcast news shows starting with only the audio data. A novel method of automatically detecting and removing commercials is presented and shown to increase the performance of the system while also reducing the computational effort required. A sophisticated large vocabulary speech recogniser which produces high-quality transcriptions of the audio and a window-based retrieval system with post-retrieval merging are also described. Results are presented using the 1999 TREC-8 Spoken Document Retrieval data for the task where no story boundaries are known. Experiments investigating the effectiveness of all aspects of the system are described, and the relative benefits of automatically eliminating commercials, enforcing broadcast structure during retrieval, using relevance feedback, changing retrieval parameters and merging during post-processing are shown. An Average Precision of 46.8%, when duplicates are scored as irrelevant, is shown to be achievable using this system, with the corresponding word error rate of the recogniser being 20.5%.

Mots clés: information retrieval; automatic speech recognition; story segmentation; commercial detection; spoken document retrieval

Domaines: Informatique [cs]; Intelligence artificielle [cs.AI]; Informatique et langage [cs.CL]; Apprentissage [cs.LG]; Multimédia [cs.MM]; Traitement du texte et du document; Statistiques [stat]; Machine Learning [stat.ML]; Applications [stat.AP]

Sue E Johnson, Pierre Jourlin, Karen Jones, Philip C Woodland. Information Retrieval from Unsegmented Broadcast News Audio. International Journal of Speech Technology, 2001, 4, pp.251 - 268. ⟨hal-02171698⟩