LEADER 04384nam 22007575 450 001 9910437900603321 005 20211006165004.0 010 $a1-283-91048-9 010 $a1-4614-4639-2 024 7 $a10.1007/978-1-4614-4639-2 035 $a(CKB)2670000000278084 035 $a(EBL)1081849 035 $a(OCoLC)819508515 035 $a(SSID)ssj0000799043 035 $a(PQKBManifestationID)11437005 035 $a(PQKBTitleCode)TC0000799043 035 $a(PQKBWorkID)10755669 035 $a(PQKB)11271909 035 $a(DE-He213)978-1-4614-4639-2 035 $a(MiAaPQ)EBC1081849 035 $a(PPN)168300818 035 $a(EXLCZ)992670000000278084 100 $a20121026d2013 u| 0 101 0 $aeng 135 $aur|n|---||||| 181 $ctxt 182 $cc 183 $acr 200 10$aPrivacy-Preserving Machine Learning for Speech Processing$b[electronic resource] /$fby Manas A. Pathak 205 $a1st ed. 2013. 210 1$aNew York, NY :$cSpringer New York :$cImprint: Springer,$d2013. 215 $a1 online resource (144 p.) 225 1 $aSpringer Theses, Recognizing Outstanding Ph.D. Research,$x2190-5053 300 $a"Doctoral thesis accepted by Carnegie Mellon University, USA". 311 $a1-4899-9120-4 311 $a1-4614-4638-4 327 $aThesis 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. 330 $aThis thesis discusses the privacy issues in speech-based applications, including biometric authentication, surveillance, and external speech processing services. Manas A. Pathak presents solutions for privacy-preserving speech processing applications such as speaker verification, speaker identification, and speech recognition. The thesis introduces tools from cryptography and machine learning and current techniques for improving the efficiency and scalability of the presented solutions, as well as experiments with prototype implementations of the solutions for execution time and accuracy on standardized speech datasets. Using the framework proposed  may make it possible for a surveillance agency to listen for a known terrorist, without being able to hear conversation from non-targeted, innocent civilians. 410 0$aSpringer Theses, Recognizing Outstanding Ph.D. Research,$x2190-5053 606 $aSignal processing 606 $aImage processing 606 $aSpeech processing systems 606 $aElectrical engineering 606 $aData structures (Computer science) 606 $aPower electronics 606 $aSignal, Image and Speech Processing$3https://scigraph.springernature.com/ontologies/product-market-codes/T24051 606 $aCommunications Engineering, Networks$3https://scigraph.springernature.com/ontologies/product-market-codes/T24035 606 $aData Structures and Information Theory$3https://scigraph.springernature.com/ontologies/product-market-codes/I15009 606 $aPower Electronics, Electrical Machines and Networks$3https://scigraph.springernature.com/ontologies/product-market-codes/T24070 615 0$aSignal processing. 615 0$aImage processing. 615 0$aSpeech processing systems. 615 0$aElectrical engineering. 615 0$aData structures (Computer science). 615 0$aPower electronics. 615 14$aSignal, Image and Speech Processing. 615 24$aCommunications Engineering, Networks. 615 24$aData Structures and Information Theory. 615 24$aPower Electronics, Electrical Machines and Networks. 676 $a004.2/1 676 $a621.3994 700 $aPathak$b Manas A$4aut$4http://id.loc.gov/vocabulary/relators/aut$0721223 906 $aBOOK 912 $a9910437900603321 996 $aPrivacy-Preserving Machine Learning for Speech Processing$92528194 997 $aUNINA