I'm working on a speech recognition project for college. I would like to know if anybody knows any benchmarks or relevant tests generally accepted in speech recognition community.
I try to do the labeling of single, separate words, but until now all my tests are based on recordings of my own voice. Any help would be appreciated.
Thank you very much!
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
There are many benchmarks for the different problem. For example if you are interested in medium vocabulary continuous speech recognition with a microphone, the good choice is WSJ database. For acoustic model research, TIMIT database is the right choice. For robust noisy speech recognition you should look on Aurora database. For broadcast news there is HUB4/HUB5.
You need to describe the problem you are trying to solve first.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello,
I'm working on a speech recognition project for college. I would like to know if anybody knows any benchmarks or relevant tests generally accepted in speech recognition community.
I try to do the labeling of single, separate words, but until now all my tests are based on recordings of my own voice. Any help would be appreciated.
Thank you very much!
There are many benchmarks for the different problem. For example if you are interested in medium vocabulary continuous speech recognition with a microphone, the good choice is WSJ database. For acoustic model research, TIMIT database is the right choice. For robust noisy speech recognition you should look on Aurora database. For broadcast news there is HUB4/HUB5.
You need to describe the problem you are trying to solve first.
@Andreea You may want to have a look at http://itl.nist.gov/iad/mig/publications/ASRhistory/index.html