I have a large group of listeners I want to test for their recognition of
nonsense English CVC words presented with an interesting masker. Would Sphynx
work? If yes, what error rate is expected? Any other suggestion?
-Pierre
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Sorry, your task is not quite clear for me. Do you want to recognize noisy
words with CMUSphinx? Why are you talking about listeners here?
Please note that decoder doesn't understand what is being said, so be it
"sensesible" word or "nonsense" word, it doesn't matter.
What does matter and affect accuracy is the amount of noise that will be
present , size of vocabulary (number of words) and so on. But since your task
is not clear, it's hard to predict the error rate. I suggest you to explain in
a more detailed way what are you trying to do.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I have a large group of listeners I want to test for their recognition of
nonsense English CVC words presented with an interesting masker. Would Sphynx
work? If yes, what error rate is expected? Any other suggestion?
-Pierre
Hello Pierre
Sorry, your task is not quite clear for me. Do you want to recognize noisy
words with CMUSphinx? Why are you talking about listeners here?
Please note that decoder doesn't understand what is being said, so be it
"sensesible" word or "nonsense" word, it doesn't matter.
What does matter and affect accuracy is the amount of noise that will be
present , size of vocabulary (number of words) and so on. But since your task
is not clear, it's hard to predict the error rate. I suggest you to explain in
a more detailed way what are you trying to do.