Read more
Multimedia Information Retrieval: Content-Based Information Retrieval from Large Text and Audio Databases addresses the future need for sophisticated search techniques that will be required to find relevant information in large digital data repositories, such as digital libraries and other multimedia databases. Because of the dramatically increasing amount of multimedia data available, there is a growing need for new search techniques that provide not only fewer bits, but also the most relevant bits, to those searching for multimedia digital data. This book serves to bridge the gap between classic ranking of text documents and modern information retrieval where composite multimedia documents are searched for relevant information.
Multimedia Information Retrieval: Content-Based Information Retrieval from Large Text and Audio Databases begins to pave the way for speech retrieval; only recently has the search for information in speech recordings become feasible. This book provides the necessary introduction to speech recognition while discussing probabilistic retrieval and text retrieval, key topics in classic information retrieval. The book then discusses speech retrieval, which is even more challenging than retrieving text documents because word boundaries are difficult to detect, and recognition errors affect the retrieval effectiveness. This book also addresses the problem of integrating information retrieval and database functions, since there is an increasing need for retrieving information from frequently changing data collections which are organized and managed by a database system.
Multimedia Information Retrieval: Content-Based Information Retrieval from Large Text and Audio Databases serves as an excellent reference source and may be used as a text for advanced courses on the topic.
List of contents
1 Introduction.- 1.1 Towards Lightweight Information.- 1.2 What is Multimedia Information Retrieval?.- 1.3 Examples of Multimedia Information Retrieval Systems.- 1.4 Vector Space Retrieval.- 1.5 Interactive Search Techniques.- 1.6 Evaluation Issues.- 1.7 Similarity Thesauri.- 2 Probabilistic Retrieval.- 2.1 Information Retrieval Events in a Probability Space.- 2.2 Cooper and Robertson's Probability Ranking Principle.- 2.3 Robertson-Sparck Jones Weighting.- 2.4 Logistic Inference Models.- 3 Text Retrieval.- 3.1 Text Characteristics.- 3.2 Vocabularies for Text Indexing.- 3.3 Weighting and Retrieval Functions.- 4 Automatic Speech Recognition.- 4.1 Speech Sound Waves.- 4.2 Digital Speech Signal Processing.- 4.3 Hidden Markov Model (HMM) Theory.- 4.4 HMM Based Recognition.- 5 Speech Retrieval.- 5.1 Introduction.- 5.2 Speech Recognition.- 5.3 Indexing and Retrieval by N-Grams.- 5.4 Indexing and Retrieval by Word Matching.- 5.5 Metadata Organisation and Query Processing.- 5.6 Recognition Errors and Retrieval Effectiveness.- 5.7 Experiments.- 6 Case Study: Retrieving Scanned Library Cards.- 6.1 Introduction.- 6.2 Probabilistic Term Weighting and Retrieval.- 6.3 Estimating Occurrence Probabilities.- 6.4 Retrieval for One-Word Queries.- 6.5 Including Ordering Information.- 7 Integrating Information Retrieval and Database Functions.- 7.1 Introduction.- 7.2 System Architecture.- 7.3 Transactions on the IR Index.- 7.4 Transaction Manager of the SPIDER IR Server.- 8 Outlook.- A Theorems and Proofs.
About the author
Peter Schäuble war Assistenzprofessor für Informatik an der ETH Zürich, wo er mit seiner Forschergruppe neue Methoden für die Informationsbeschaffung entwickelte. Heute leitet er die von ihm gegründete Eurospider Information Technology AG, welche Software für die Suche, Filterung und Kategorisierung von Informationen anbietet.
