Title | ||
---|---|---|
Vulnerability of Voice Verification Systems to Spoofing Attacks by TTS Voices Based on Automatically Labeled Telephone Speech. |
Abstract | ||
---|---|---|
This paper explores the robustness of a text-dependent voice verification system against spoofing attacks that use synthesized speech based on automatically labeled telephone speech. Our experiments show that when manual labeling is not used in creating the synthesized voice, and the voice is based on telephone speech rather than studio recordings, False Acceptance error rate decreases significantly compared to high-quality synthesized speech. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1007/978-3-319-11581-8_59 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
spoofing,speech synthesis,unit selection,HMM,speaker recognition | Speech synthesis,Spoofing attack,Computer science,Word error rate,Robustness (computer science),Speech recognition,Speaker recognition,Hidden Markov model,Verification system,Vulnerability | Conference |
Volume | ISSN | Citations |
8773 | 0302-9743 | 4 |
PageRank | References | Authors |
0.42 | 4 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vadim Shchemelinin | 1 | 26 | 4.56 |
Mariia Topchina | 2 | 4 | 0.42 |
Konstantin Simonchik | 3 | 28 | 6.52 |