Published January 1, 2016
| Version v1
Journal article
Open
Anti-Spoofing for Text-Independent Speaker Verification: An Initial Database, Comparison of Countermeasures, and Human Performance
Creators
- 1. Univ Edinburgh, Ctr Speech Technol Res, Edinburgh EH8 9AB, Midlothian, Scotland
- 2. New Mexico State Univ, Klipsch Sch Elect & Comp Engn, Las Cruces, NM 88003 USA
- 3. Ozyegin Univ, TR-34662 Istanbul, Turkey
- 4. Univ Sci & Technol China, Hefei 230027, Peoples R China
- 5. Univ Tokyo, Tokyo 1130033, Japan
- 6. Nagoya Univ, Ctr Informat Technol, Nagoya, Aichi 4648601, Japan
Description
In this paper, we present a systematic study of the vulnerability of automatic speaker verification to a diverse range of spoofing attacks. We start with a thorough analysis of the spoofing effects of five speech synthesis and eight voice conversion systems, and the vulnerability of three speaker verification systems under those attacks. We then introduce a number of countermeasures to prevent spoofing attacks from both known and unknown attackers. Known attackers are spoofing systems whose output was used to train the countermeasures, while an unknown attacker is a spoofing system whose output was not available to the countermeasures during training. Finally, we benchmark automatic systems against human performance on both speaker verification and spoofing detection tasks.
Files
bib-665a0982-19b7-4492-93aa-a3be06daae3f.txt
Files
(352 Bytes)
| Name | Size | Download all |
|---|---|---|
|
md5:4dc25b9502af0842fb1a42ede4d329ba
|
352 Bytes | Preview Download |