Can CMU Sphinx be used to evaluate pronunciation? If it is ok, how to do?
I know OpenEars have recognitionScore,but the score is not what i want.
http://www.politepix.com/forums/topic/some-problems-about-pronunciation-evaluation/
"they can only be used to compare the same utterances within a single session. Meaning that you can gather scores about a number of utterances of the same statement from a single speaker in a single environment in a single app session and say that some scores are better than others and give that feedback to the user if you want. But you can never compare scores across multiple speakers, multiple devices, and multiple usage sessions in order to derive meaningful information, such as saying that a word utterance with a score of -2000 should always be understood to be a correct pronunciation."
Thanks
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Can CMU Sphinx be used to evaluate pronunciation? If it is ok, how to do?
I know OpenEars have recognitionScore,but the score is not what i want.
http://www.politepix.com/forums/topic/some-problems-about-pronunciation-evaluation/
"they can only be used to compare the same utterances within a single session. Meaning that you can gather scores about a number of utterances of the same statement from a single speaker in a single environment in a single app session and say that some scores are better than others and give that feedback to the user if you want. But you can never compare scores across multiple speakers, multiple devices, and multiple usage sessions in order to derive meaningful information, such as saying that a word utterance with a score of -2000 should always be understood to be a correct pronunciation."
Thanks
No
See also
http://cmusphinx.sourceforge.net/wiki/faq?&#qhow_to_implement_pronunciation_evaluation