This paper reports on a new application of the Markov model to an automatic speech recognition system, in which the feature vectors of speech are regarded to represent the states and the output symbols of the Markov model. The transition-probability of the states and the symbol-output probability are assumed to be represented by multidimensional normal density functions of the feature vector. The DP-matching algorithm is used for calculating optimum time sequence of observed feature vectors. In order to confirm the efficiency of this system, we compared experimentally performance of this system to that of other approaches, such as those using Maharanobis' distance or Euclidean distance. Based on experimentation, in a speaker independent mode, using a vocabulary of Japanese single-digit and four-digit numerals, the current system is shown to be more effective than others.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Tomio TAKARA, Tomoki YAKABU, "Connected Spoken Word Recognition Using the Markov Model for the Feature Vector" in IEICE TRANSACTIONS on Fundamentals,
vol. E74-A, no. 7, pp. 1788-1796, July 1991, doi: .
Abstract: This paper reports on a new application of the Markov model to an automatic speech recognition system, in which the feature vectors of speech are regarded to represent the states and the output symbols of the Markov model. The transition-probability of the states and the symbol-output probability are assumed to be represented by multidimensional normal density functions of the feature vector. The DP-matching algorithm is used for calculating optimum time sequence of observed feature vectors. In order to confirm the efficiency of this system, we compared experimentally performance of this system to that of other approaches, such as those using Maharanobis' distance or Euclidean distance. Based on experimentation, in a speaker independent mode, using a vocabulary of Japanese single-digit and four-digit numerals, the current system is shown to be more effective than others.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e74-a_7_1788/_p
Copy
@ARTICLE{e74-a_7_1788,
author={Tomio TAKARA, Tomoki YAKABU, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Connected Spoken Word Recognition Using the Markov Model for the Feature Vector},
year={1991},
volume={E74-A},
number={7},
pages={1788-1796},
abstract={This paper reports on a new application of the Markov model to an automatic speech recognition system, in which the feature vectors of speech are regarded to represent the states and the output symbols of the Markov model. The transition-probability of the states and the symbol-output probability are assumed to be represented by multidimensional normal density functions of the feature vector. The DP-matching algorithm is used for calculating optimum time sequence of observed feature vectors. In order to confirm the efficiency of this system, we compared experimentally performance of this system to that of other approaches, such as those using Maharanobis' distance or Euclidean distance. Based on experimentation, in a speaker independent mode, using a vocabulary of Japanese single-digit and four-digit numerals, the current system is shown to be more effective than others.},
keywords={},
doi={},
ISSN={},
month={July},}
Copy
TY - JOUR
TI - Connected Spoken Word Recognition Using the Markov Model for the Feature Vector
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1788
EP - 1796
AU - Tomio TAKARA
AU - Tomoki YAKABU
PY - 1991
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E74-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 1991
AB - This paper reports on a new application of the Markov model to an automatic speech recognition system, in which the feature vectors of speech are regarded to represent the states and the output symbols of the Markov model. The transition-probability of the states and the symbol-output probability are assumed to be represented by multidimensional normal density functions of the feature vector. The DP-matching algorithm is used for calculating optimum time sequence of observed feature vectors. In order to confirm the efficiency of this system, we compared experimentally performance of this system to that of other approaches, such as those using Maharanobis' distance or Euclidean distance. Based on experimentation, in a speaker independent mode, using a vocabulary of Japanese single-digit and four-digit numerals, the current system is shown to be more effective than others.
ER -