Would it be helpful in Speech Recognition especially in acoustic model to replace CTC with ACE?

[nemoramo]

Hello, I am writing this topic to ask if it will be useful in speech recognition tasks. I am going to test your ACE loss on my acoustic model. Hope it can produce comparable performance. I will show the result later.

[summerlvsong]

Yes, after feature extraction, there is no much difference between acoustic model and OCR model.