Triphone

In linguistics, a triphone is a sequence of three phonemes. Triphones are useful in models of natural language processing where they are used to… (More)
Wikipedia

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
2014
2014
It is well-known in machine learning that multitask learning (MTL) can help improve the generalization performance of singly… (More)
  • figure 1
  • table 1
  • table 2
  • figure 2
  • table 3
Is this relevant?
2013
2013
State tying effectively strikes a balance between detailed modeling and robust parameter estimation for hidden Markov models… (More)
  • figure 1
  • figure 2
  • figure 3
  • table 3
Is this relevant?
Highly Cited
2012
Highly Cited
2012
We propose a novel context-dependent (CD) model for large-vocabulary speech recognition (LVSR) that leverages recent advances in… (More)
  • figure 1
  • table I
  • table II
  • table IV
  • table V
Is this relevant?
2012
2012
In this paper we revisit the recently proposed triphone mapping as an alternative to decision tree state clustering. We… (More)
  • figure 1
  • table 1
  • table 2
Is this relevant?
2011
2011
This paper presents effective triphone mapping for acoustic models training in automatic speech recognition, which allows the… (More)
  • figure 1
  • table 1
  • figure 2
Is this relevant?
2007
2007
The Polish text corpus was analysed to find information about phoneme statistics. We were especially interested in triphones as… (More)
  • figure 1
  • figure 2
  • table 1
  • figure 3
  • table 2
Is this relevant?
2005
2005
In this paper, the syllable, an alternative phonetic unit to the phone, is researched in the context of speech synthesis. Several… (More)
  • figure 1
  • figure 3
  • figure 5
Is this relevant?
Highly Cited
2001
Highly Cited
2001
In order to help understand why gains in pronunciation modeling have proven so elusive, we investigated which kinds of… (More)
  • figure 1
Is this relevant?
1998
1998
A crucial issue in triphone based continuous speech recognition is the large number of models to be estimated against the limited… (More)
  • table I
  • table II
  • table III
Is this relevant?
Highly Cited
1995
Highly Cited
1995
A method of speaker adaptation for continuous density hidden Markov models (HMMs) is presented. An initial speaker-independent… (More)
  • figure 1
  • figure 2
  • figure 3
Is this relevant?