Is/are there any standard audio corpora available that could be used for qualifying a speaker verification system with following description ?
The system in question is a simple one that expects user to record a password (couple of times) as a registration step. The system is then supposed to "accept" only if the "same user" speaks the password that was recorded and reject any other password/speaker.
Thanks and regards,
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi,
Is/are there any standard audio corpora available that could be used for qualifying a speaker verification system with following description ?
The system in question is a simple one that expects user to record a password (couple of times) as a registration step. The system is then supposed to "accept" only if the "same user" speaks the password that was recorded and reject any other password/speaker.
Thanks and regards,
You can use any speech recognition database which has speaker marks for that. For example TEDLIUM US English database.