https://github.com/cran/dtw
Tip revision: 47b430f6e116f153b5f406d88ce26f868027a447 authored by Toni Giorgino on 30 November 2007, 00:00:00 UTC
version 1.0-2
version 1.0-2
Tip revision: 47b430f
dtw.bib
@ARTICLE{Sakoe1978,
title = {Dynamic programming algorithm optimization for spoken word recognition},
author = {Sakoe, H. and Chiba, S.},
journal = {Acoustics, Speech, and Signal Processing [see also {IEEE} Transactions on Signal Processing], {IEEE} Transactions on},
year = {1978},
volume = {26},
number = {1},
pages = {43--49},
month = feb,
abstract = {This paper reports on an optimum dynamic progxamming (DP) based time-
normalization algorithm for spoken word recognition. First, a
general principle of time-normalization is given using time-
warping function. Then, two time-normalized distance
definitions, called symmetric and asymmetric forms, are derived
from the principle. These two forms are compared with each
other through theoretical discussions and experimental studies.
The symmetric form algorithm superiority is established. A new
technique, called slope constraint, is successfully introduced,
in which the warping function slope is restricted so as to
improve discrimination between words in different categories.
The effective slope constraint characteristic is qualitatively
analyzed, and the optimum slope constraint condition is
determined through experiments. The optimized algorithm is then
extensively subjected to experimental comparison with various
DP-algorithms, previously applied to spoken word recognition by
different research groups. The experiment shows that the
present algorithm gives no more than about two-thirds errors,
even compared to the best conventional algorithm.},
ISSN = {0096-3518},
}
@ARTICLE{Itakura1975,
title = {Minimum prediction residual principle applied to speech recognition},
author = {Itakura, F.},
journal = {Acoustics, Speech, and Signal Processing [see also {IEEE} Transactions on Signal Processing], {IEEE} Transactions on},
year = {1975},
volume = {23},
number = {1},
pages = {67--72},
month = feb,
abstract = {A computer system is described in which isolated words, spoken by a
designated talker, are recognized through calculation of a
minimum prediction residual. A reference pattern for each word
to be recognized is stored as a time pattern of linear
prediction coefficients (LPC). The total log prediction
residual of an input signal is minimized by optimally
registering the reference LPC onto the input autocorrelation
coefficients using the dynamic programming algorithm (DP). The
input signal is recognized as the reference word which produces
the minimum prediction residual. A sequential decision
procedure is used to reduce the amount of computation in DP. A
frequency normalization with respect to the long-time spectral
distribution is used to reduce effects of variations in the
frequency response of telephone connections. The system has
been implemented on a DDP-516 computer for the 200-word
recognition experiment. The recognition rate for a designated
male talker is 97.3 percent for telephone input, and the
recognition time is about 22 times real time.},
ISSN = {0096-3518},
}
@article{Velichko,
author = {V. M. Velichko and N. G. Zagoruyko},
title = {Automatic Recognition of 200 Words},
journal = {International Journal of Man-Machine Studies},
volume = {2},
issue = {3},
year = {1970},
pages = {223-234},
bibsource = {http://www.interaction-design.org/references/},
}
@ARTICLE{White1976,
title = {Speech recognition experiments with linear predication, bandpass filtering, and dynamic programming},
author = {White, G. and Neely, R.},
journal = {Acoustics, Speech, and Signal Processing [see also {IEEE} Transactions on Signal Processing], {IEEE} Transactions on},
year = {1976},
volume = {24},
number = {2},
pages = {183--188},
month = apr,
abstract = {Automatic speech recognition experiments are described in which
several popular preprocessing and classification strategies are
compared. Preprocessing is done either by linear predictive
analysis or by bandpass filtering. The two approaches are shown
to produce similar recognition scores. The classifier uses
either linear time stretching or dynamic programming to achieve
time alignment. It is shown that dynamic programming is of
major importance for recognition of polysyllabic words. The
speech is compressed into a quasi-phoneme character string or
preserved uncompressed. Best results are obtained with
uncompressed data, using nonlinear time registration for
multisyllabic words.},
ISSN = {0096-3518},
}