Need help in speech recognition?

Want to understand the topic. A good idea of how the decoding of phonemes to words and gammatech. But it is absolutely not guided in the first stages of signal processing: signal -> vector feature -> phonemes.


May be someone doing it. It would make links to articles and tools for decoding the signal into a vector of features and phonemes, and the corresponding dictionaries. Looked diagonally cmu-sphinx, flying is not understood.


Thank you.
October 8th 19 at 03:49
1 answer
October 8th 19 at 03:51
Can start, for example, the HTK Toolkit. There is a link to a book in which there is a first theory. The Toolkit uses hidden Markov models for recognition.
I tried to download it once. I think I stopped the registration. Now I will try again. Thanks for the tip. - Gustave.Ha commented on October 8th 19 at 03:54

Find more questions by tags Speech recognition