- This topic has 1 reply, 2 voices, and was last updated 8 years ago by .
Viewing 1 reply thread
Viewing 1 reply thread
- You must be logged in to reply to this topic.
› Forums › Automatic speech recognition › Hidden Markov Models (HMMs) › Triphone definition
I was looking at some past papers and I was unsure if I am confusing the definition of a triphone.
I am under the impression that a triphone is a subphone unit that makes up a third of a phone. However, I don’t remember if there is a particular name for a sequence of three phones, e.g. for n-gram 3 words is considered a trigram, is the same true for phones?
What is the correct term for a sequence of 3 subphones used in HMM ASR?
What is the correct term for a sequence of 3 phones?
The terminology is potentially confusing.
A triphone is a model of one whole phone. It’s not a model of a fraction of a phone, and it’s not a model of a sequence of three phones.
It’s called triphone because it takes a context of three phones into account (previous, current and next). So, it’s a context-dependent model of a phone. Depending on the amount of context we take into account, we use different terms to describe a model of a phone:
(Note that a biphone model is not a model of a diphone!)
Jurafsky and Martin’s explanations may not be the clearest, especially when they start talking about “sub-phones”. By that, they simply mean the states within an HMM.
Some forums are only available if you are logged in. Searching will only return results from those forums if you log in.
Copyright © 2024 · Balance Child Theme on Genesis Framework · WordPress · Log in