@inbook{6621d99c26af419e8741fc1b079d5357,
title = "Speech Indexing",
abstract = "This chapter will focus on the automatic extraction of information from the speech in multimedia documents. This approach is often referred to as speech indexing and it can be regarded as a subfield of audio indexing that also incorporates for example the analysis of music and sounds. If the objective of the recognition of the words spoken is to support retrieval, one commonly speaks of spoken document retrieval (SDR). If the objective is on the coupling of various media types the term media mining or even cross-media mining is used. Most attention in this chapter will go to SDR. The focus is less on searching (an index of ) a multimedia database, but on enabling multiple views on the data by cross-linking all the available multifaceted information sources in a multimedia database. In section 1.6 cross-media mining will be discussed in more detail.",
keywords = "EWI-11008, HMI-MR: MULTIMEDIA RETRIEVAL, HMI-SLT: Speech and Language Technology, IR-61901, Audio search, Speech Indexing, Speech Recognition, Spoken Document Retrieval, METIS-241883",
author = "Ordelman, {Roeland J.F.} and {de Jong}, {Franciska M.G.} and {van Leeuwen}, D.A.",
note = "http://eprints.ewi.utwente.nl/11008 ",
year = "2007",
doi = "10.1007/978-3-540-72895-5_7",
language = "Undefined",
isbn = "978-3-540-72894-8",
series = "Data-Centric Systems and Applications",
publisher = "Springer",
number = "LNCS4549",
pages = "199--224",
editor = "Henk Blanken and {de Vries}, A.P. and H.E. Blok and L. Feng",
booktitle = "Multimedia Retrieval",
address = "Germany",
}