1

As far as I know, neural networks have hidden computational units and HMM has hidden states.

Hidden Markov Models can be used to generate a language, that is, list elements from a family of strings. For example, if you have an HMM that models a set of sequences, you would be able to generate members of this family, by listing sequences that would befall into the group of sequences we are modeling.

In this, this and this paper, HMMs are combined with ANNs. But how exactly? What is a Hidden Markov Model - Artificial Neural Network (HMM-ANN)? Is HMM-ANN a hybrid algorithm? In simple words, how is this model or algorithm used?

nbro
  • 39,006
  • 12
  • 98
  • 176
Pluviophile
  • 1,223
  • 5
  • 17
  • 37
  • Where did you find this expression "Hidden Markov Model - Artificial Neural Network"? – nbro May 17 '20 at 10:55
  • 1
    [Here](https://dl.acm.org/doi/pdf/10.1145/3379247.3379276) and [here](https://ieeexplore.ieee.org/document/5232417) [HMM-ANN](https://www.researchgate.net/publication/33702866_Hidden_Markov_models_and_artificial_neural_networks_for_speech_and_speaker_recognition) – Pluviophile May 17 '20 at 12:28
  • In these 3 papers, are you sure they are referring to the same model? Because if not this question may become a little bit too broad, because you would be asking us to explain different models. Maybe HMMs are combined with ANNs in different ways in these papers. – nbro May 17 '20 at 12:50
  • Yes, they are referring the same(Speech Recognition). – Pluviophile May 17 '20 at 12:55
  • I was asking if they were referring to the same model, not if they were being used for the same purpose or task. Are you sure that, in these papers, they are using the same model? – nbro May 18 '20 at 13:06
  • According to my knowledge, Yes they are referring the same model, – Pluviophile May 18 '20 at 13:25

0 Answers0