Skip to search formSkip to main content
You are currently offline. Some features of the site may not work correctly.

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… Expand
Wikipedia

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
Highly Cited
2010
Highly Cited
2010
Robustly detecting keywords in human speech is an important precondition for cognitive systems, which aim at intelligently… Expand
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • figure 5
Is this relevant?
Highly Cited
2009
Highly Cited
2009
We apply Hidden Conditional Random Fields (HCRFs) to the task of TIMIT phone recognition. HCRFs are discriminatively trained… Expand
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • table I
Is this relevant?
2007
2007
This work presents a novel approach to generating phonetic units in order to recognize mixed-language or multilingual speech… Expand
  • table 1
  • table 2
  • figure 1
  • figure 2
  • table 3
Is this relevant?
Highly Cited
2007
Highly Cited
2007
  • L. Xie, Z. Liu
  • IEEE Transactions on Multimedia
  • 2007
  • Corpus ID: 16584961
This paper presents an articulatory modelling approach to convert acoustic speech into realistic mouth animation. We directly… Expand
  • figure 1
  • table I
  • figure 3
  • figure 4
  • figure 5
Is this relevant?
2004
2004
We introduce a discriminative training algorithm for the estimation of hidden Markov model (HMM) parameters. This algorithm is… Expand
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • table II
Is this relevant?
Highly Cited
2001
Highly Cited
2001
A statistical model for segmentation and word discovery in continuous speech is presented. An incremental unsupervised learning… Expand
Is this relevant?
Highly Cited
1998
Highly Cited
1998
  • J. Ming, F. Smith
  • Proceedings of the IEEE International Conference…
  • 1998
  • Corpus ID: 17872406
A crucial issue in triphone based continuous speech recognition is the large number of models to be estimated against the limited… Expand
  • table 11
  • table 111
  • table I
Is this relevant?
Highly Cited
1995
Highly Cited
1995
Abstract A method of speaker adaptation for continuous density hidden Markov models (HMMs) is presented. An initial speaker… Expand
  • figure 1
  • figure 2
  • figure 3
Is this relevant?
Highly Cited
1994
Highly Cited
1994
A process for increasing the proportion of a gas in a gaseous mixture comprising such gas and at least two other constituents… Expand
  • figure 1
  • figure 2
  • table 1
  • table 2
  • table 4
Is this relevant?
1989
1989
SRI has developed a speaker-independent continuous speech, large vocabulary speech recognition system, DECIPHER, that provides… Expand
  • table 1
  • table 2
  • table 3
Is this relevant?