Abstract
In this chapter, we develop a method for speaker verification that requires minimal computation overhead needed to satisfy the privacy constraints. The central aspect of our approach is to reduce the speaker verification task to string comparison. Instead of using the UBM-GMM approach, we convert the utterances into supervector features (Campbell et al., 2006) that are invariant with the length of the utterance. By applying the locality sensitive hashing (LSH) transformation (Gionis et al., 1999) to the supervectors, we reduce the problem of nearest-neighbor classification into string comparison. It is very efficient to perform string comparison with privacy, similar to a conventional password system. By applying a cryptographic hash function, e.g., SHA-256 (SHA 2008), we convert the LSH transformation to an obfuscated string which the server cannot use to gain information about the supervectors, but is still able to compare if two strings are identical. This one-way transformation preserves the privacy of the speech utterances submitted by the user, and can be executed significantly faster than applying homomorphic encryption.
Keywords
- Speaker Verification
- String Comparison
- Supervector Features
- Privacy Constraints
- Locality Sensitive Hashing (LSH)
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Campbell JP (1995) Testing with the YOHO CD-ROM voice verification corpus. In: IEEE international conference on acoustics, speech and signal processing
Campbell WM, Sturim DE, Reynolds DA, Solomonoff A (2006) SVM based speaker verification using a GMM supervector kernel and NAP variability compensation. In: IEEE international conference on acoustics, speech and signal processing
Aristides G, Piotr I, and Rajeev M (1999) Similarity search in high dimensions via hashing. In: Proceedings of the twenty-fifth international conference on very large databases, pp 518–529
SHA (2008) FIPS 180–3: Secure hash standard. National Institute for Standards and Technology
OpenSSL (2010). http://www.openssl.org/docs/crypto/bn.html
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2013 Springer Science+Business Media New York
About this chapter
Cite this chapter
Pathak, M.A. (2013). Privacy-Preserving Speaker Verification as String Comparison. In: Privacy-Preserving Machine Learning for Speech Processing. Springer Theses. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-4639-2_6
Download citation
DOI: https://doi.org/10.1007/978-1-4614-4639-2_6
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-4638-5
Online ISBN: 978-1-4614-4639-2
eBook Packages: EngineeringEngineering (R0)