04384nam 22007575 450 991043790060332120211006165004.01-283-91048-91-4614-4639-210.1007/978-1-4614-4639-2(CKB)2670000000278084(EBL)1081849(OCoLC)819508515(SSID)ssj0000799043(PQKBManifestationID)11437005(PQKBTitleCode)TC0000799043(PQKBWorkID)10755669(PQKB)11271909(DE-He213)978-1-4614-4639-2(MiAaPQ)EBC1081849(PPN)168300818(EXLCZ)99267000000027808420121026d2013 u| 0engur|n|---|||||txtccrPrivacy-Preserving Machine Learning for Speech Processing[electronic resource] /by Manas A. Pathak1st ed. 2013.New York, NY :Springer New York :Imprint: Springer,2013.1 online resource (144 p.)Springer Theses, Recognizing Outstanding Ph.D. Research,2190-5053"Doctoral thesis accepted by Carnegie Mellon University, USA".1-4899-9120-4 1-4614-4638-4 Thesis Overview -- Speech Processing Background -- Privacy Background -- Overview of Speaker Verification with Privacy -- Privacy-Preserving Speaker Verification Using Gaussian Mixture Models -- Privacy-Preserving Speaker Verification as String Comparison -- Overview of Speaker Identification with Privacy -- Privacy-Preserving Speaker Identification Using Gausian Mixture Models -- Privacy-Preserving Speaker Identification as String Comparison -- Overview of Speech Recognition with Privacy -- Privacy-Preserving Isolated-Word Recognition -- Thesis Conclusion -- Future Work -- Differentially Private Gaussian Mixture Models.This thesis discusses the privacy issues in speech-based applications, including biometric authentication, surveillance, and external speech processing services. Manas A. Pathak presents solutions for privacy-preserving speech processing applications such as speaker verification, speaker identification, and speech recognition. The thesis introduces tools from cryptography and machine learning and current techniques for improving the efficiency and scalability of the presented solutions, as well as experiments with prototype implementations of the solutions for execution time and accuracy on standardized speech datasets. Using the framework proposed  may make it possible for a surveillance agency to listen for a known terrorist, without being able to hear conversation from non-targeted, innocent civilians.Springer Theses, Recognizing Outstanding Ph.D. Research,2190-5053Signal processingImage processingSpeech processing systemsElectrical engineeringData structures (Computer science)Power electronicsSignal, Image and Speech Processinghttps://scigraph.springernature.com/ontologies/product-market-codes/T24051Communications Engineering, Networkshttps://scigraph.springernature.com/ontologies/product-market-codes/T24035Data Structures and Information Theoryhttps://scigraph.springernature.com/ontologies/product-market-codes/I15009Power Electronics, Electrical Machines and Networkshttps://scigraph.springernature.com/ontologies/product-market-codes/T24070Signal processing.Image processing.Speech processing systems.Electrical engineering.Data structures (Computer science).Power electronics.Signal, Image and Speech Processing.Communications Engineering, Networks.Data Structures and Information Theory.Power Electronics, Electrical Machines and Networks.004.2/1621.3994Pathak Manas Aauthttp://id.loc.gov/vocabulary/relators/aut721223BOOK9910437900603321Privacy-Preserving Machine Learning for Speech Processing2528194UNINA