03312nam 2200649Ia 450 991043790060332120200520144314.0978128391048412839104899781461446392146144639210.1007/978-1-4614-4639-2(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)99267000000027808420120918d2012 uy 0engur|n|---|||||txtccrPrivacy-preserving machine learning for speech processing /Manas A. Pathak1st ed. 2013.New York Springer20121 online resource (144 p.)Springer theses"Doctoral thesis accepted by Carnegie Mellon University, USA".9781489991201 1489991204 9781461446385 1461446384 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,2190-5053Speech processing systemsMachine learningSpeech processing systems.Machine learning.004.2/1621.3994Pathak Manas A721223MiAaPQMiAaPQMiAaPQBOOK9910437900603321Privacy-Preserving Machine Learning for Speech Processing2528194UNINA