Information Retrieval Techniques for Speech Applications

Download or read book Information Retrieval Techniques for Speech Applications written by Anni R. Coden and published by Springer. This book was released on 2003-07-31 with total page 119 pages. Available in PDF, EPUB and Kindle. Book excerpt: This volume is based on a workshop held on September 13, 2001 in New Orleans, LA, USA as part of the24thAnnualInternationalACMSIGIRConferenceon ResearchandDevelopmentinInformationRetrieval.Thetitleoftheworkshop was: “Information Retrieval Techniques for Speech Applications.” Interestinspeechapplicationsdatesbackanumberofdecades.However, it is only in the last few years that automatic speech recognition has left the con?nes of the basic research lab and become a viable commercial application. Speech recognition technology has now matured to the point where speech can be used to interact with automated phone systems, control computer programs, andevencreatememosanddocuments.Movingbeyondcomputercontroland dictation, speech recognition has the potential to dramatically change the way we create,capture,andstoreknowledge.Advancesinspeechrecognitiontechnology combined with ever decreasing storage costs and processors that double in power every eighteen months have set the stage for a whole new era of applications that treat speech in the same way that we currently treat text. The goal of this workshop was to explore the technical issues involved in a- lying information retrieval and text analysis technologies in the new application domainsenabledbyautomaticspeechrecognition.Thesepossibilitiesbringwith themanumberofissues,questions,andproblems.Speech-baseduserinterfaces create di?erent expectations for the end user, which in turn places di?erent - mands on the back-end systems that must interact with the user and interpret theuser’scommands.Speechrecognitionwillneverbeperfect,soanalyses- plied to the resulting transcripts must be robust in the face of recognition errors. The ability to capture speech and apply speech recognition on smaller, more - werful, pervasive devices suggests that text analysis and mining technologies can be applied in new domains never before considered.