Is GOPT designed to take only complete words and sentences? What about a phoneme?

[TheoSeo93]

Hi again :) Thanks to your response, I was able to replicate the whole process of pronunciation assessment.
I became curious whether this gopt can provide the accuracy of a phoneme separately without giving a complete word or sentence. So I understand this can take a sentence or a word to provide the accuracy of the level deep down to the phonemes, but can it still generate the accuracy of phoneme, given that I manually pass a text like "A" along with the correct phonetic transcription of "AH" ?
I wasn't so sure if this is designed to take only complete words or sentences, or it can take singular phoneme separately.

Thank you very much
Best regards
Theo Seo

[YuanGongND]

Yes - I think the main reason why GOPT outperforms the baseline is it takes context into consideration, i.e., it takes input sequence longer than a single phone. The input sequence, however, doesn't have to be a full sentence, it can be a word or a phrase.

If you are interested in context-independent single-phone classification, that is our baseline, and is implemented in the original Kaldi/gop recipe, which I believe is an implementation of the following paper.

Hu, W., Qian, Y., Soong, F. K., & Wang, Y. (2015). Improved mispronunciation detection with deep neural network trained acoustic models and transfer learning based logistic regression classifiers. Speech Communication, 67(January), 154-166.

-Yuan