Audio voicePA Presentation Attack Database Access API for Bob
voicePA Database Interface for Bob
This package is part of the signal-processing and machine learning toolbox Bob. It contains the access API and descriptions for the voicePA Database. The database focuses on speech presentation attacks. For the genuine data, it contains speech recordings from AVspoof, which include speech from 44 persons (31 males and 13 females) performed during the course of two months in four different sessions.
The database contains large number of different presentation attacks, obtained by replaying different type of speech, including recorded speech, voice conversion, and speech synthesis, to microphones of different devices (laptop, iPhone 3GS, and Samsung S3) using different speakers (high quality speakers, laptop, iPhone 6S, iPhone 3GS, and Samsung S3) and in different environments (two office rooms and a conference room).
This package contains the Bob-compliant interface implementation with methods to use the database directly from Python with provided protocols.
Complete Bob’s installation instructions. Then, to install this package, run:
$ conda install bob.db.voicepa
For questions or reporting issues to this software package, contact our devopment mailing list.
Release history Release notifications | RSS feed
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size bob.db.voicepa-1.1.5.zip (2.4 MB)||File type Source||Python version None||Upload date||Hashes View|