इसे छोड़कर सामग्री पर बढ़ने के लिए

Modification of entropy-based algorithm for determining words boundaries in noisy conditions

A modification of the algorithm for finding word boundaries in continuous speech based on an analysis of the entropy of a speech signal is described. At the preprocessing stage, the signal is divided into frames; the entropy value is calculated for each frame and compared with the threshold value of...

पूर्ण विवरण

में बचाया:
ग्रंथसूची विवरण
मुख्य लेखकों: Karpov, A. S., Карпов, А. С., Drozdova, V. I., Дроздова, В. И., Shagrova, G. V., Шагрова, Г. В., Romanenko, M. G., Романенко, М. Г.
स्वरूप: Статья
भाषा:English
प्रकाशित: Institute of Physics Publishing 2020
विषय:
ऑनलाइन पहुंच:https://dspace.ncfu.ru/handle/20.500.12258/13727
टैग : टैग जोड़ें
कोई टैग नहीं, इस रिकॉर्ड को टैग करने वाले पहले व्यक्ति बनें!
id ir-20.500.12258-13727
record_format dspace
spelling ir-20.500.12258-137272020-09-02T12:14:31Z Modification of entropy-based algorithm for determining words boundaries in noisy conditions Karpov, A. S. Карпов, А. С. Drozdova, V. I. Дроздова, В. И. Shagrova, G. V. Шагрова, Г. В. Romanenko, M. G. Романенко, М. Г. Entropy-based algorithm Determining words Boundaries in noisy conditions Modification of entropy-based algorithm A modification of the algorithm for finding word boundaries in continuous speech based on an analysis of the entropy of a speech signal is described. At the preprocessing stage, the signal is divided into frames; the entropy value is calculated for each frame and compared with the threshold value of the entropy γ. The algorithm is carried out in two stages, first a rough and then more precise definition of the word boundaries is made. At each stage, its own minimum distance between words is used. A modification is proposed, which consists in the fact that the entropy threshold γ is determined on the basis of the calculated SNR coefficient taking into account the experimental selection of signal parameters at the stage of precise determination of word boundaries in a noisy speech signal. Checking the functionality of the modified algorithm on noisy signals has shown that taking into account the effect of SNR on the selection of signal parameters increases the accuracy of word boundary determination 2020-09-02T12:12:04Z 2020-09-02T12:12:04Z 2020 Статья Karpov, A.S., Drozdova, V.I., Shagrova, G.V., Romanenko, M.G. Modification of entropy-based algorithm for determining words boundaries in noisy conditions // IOP Conference Series: Materials Science and Engineering. - 2020. - Volume 873. - Issue 1. - Номер статьи 012011 http://hdl.handle.net/20.500.12258/13727 en IOP Conference Series: Materials Science and Engineering application/pdf Institute of Physics Publishing
institution СКФУ
collection Репозиторий
language English
topic Entropy-based algorithm
Determining words
Boundaries in noisy conditions
Modification of entropy-based algorithm
spellingShingle Entropy-based algorithm
Determining words
Boundaries in noisy conditions
Modification of entropy-based algorithm
Karpov, A. S.
Карпов, А. С.
Drozdova, V. I.
Дроздова, В. И.
Shagrova, G. V.
Шагрова, Г. В.
Romanenko, M. G.
Романенко, М. Г.
Modification of entropy-based algorithm for determining words boundaries in noisy conditions
description A modification of the algorithm for finding word boundaries in continuous speech based on an analysis of the entropy of a speech signal is described. At the preprocessing stage, the signal is divided into frames; the entropy value is calculated for each frame and compared with the threshold value of the entropy γ. The algorithm is carried out in two stages, first a rough and then more precise definition of the word boundaries is made. At each stage, its own minimum distance between words is used. A modification is proposed, which consists in the fact that the entropy threshold γ is determined on the basis of the calculated SNR coefficient taking into account the experimental selection of signal parameters at the stage of precise determination of word boundaries in a noisy speech signal. Checking the functionality of the modified algorithm on noisy signals has shown that taking into account the effect of SNR on the selection of signal parameters increases the accuracy of word boundary determination
format Статья
author Karpov, A. S.
Карпов, А. С.
Drozdova, V. I.
Дроздова, В. И.
Shagrova, G. V.
Шагрова, Г. В.
Romanenko, M. G.
Романенко, М. Г.
author_facet Karpov, A. S.
Карпов, А. С.
Drozdova, V. I.
Дроздова, В. И.
Shagrova, G. V.
Шагрова, Г. В.
Romanenko, M. G.
Романенко, М. Г.
author_sort Karpov, A. S.
title Modification of entropy-based algorithm for determining words boundaries in noisy conditions
title_short Modification of entropy-based algorithm for determining words boundaries in noisy conditions
title_full Modification of entropy-based algorithm for determining words boundaries in noisy conditions
title_fullStr Modification of entropy-based algorithm for determining words boundaries in noisy conditions
title_full_unstemmed Modification of entropy-based algorithm for determining words boundaries in noisy conditions
title_sort modification of entropy-based algorithm for determining words boundaries in noisy conditions
publisher Institute of Physics Publishing
publishDate 2020
url https://dspace.ncfu.ru/handle/20.500.12258/13727
work_keys_str_mv AT karpovas modificationofentropybasedalgorithmfordeterminingwordsboundariesinnoisyconditions
AT karpovas modificationofentropybasedalgorithmfordeterminingwordsboundariesinnoisyconditions
AT drozdovavi modificationofentropybasedalgorithmfordeterminingwordsboundariesinnoisyconditions
AT drozdovavi modificationofentropybasedalgorithmfordeterminingwordsboundariesinnoisyconditions
AT shagrovagv modificationofentropybasedalgorithmfordeterminingwordsboundariesinnoisyconditions
AT šagrovagv modificationofentropybasedalgorithmfordeterminingwordsboundariesinnoisyconditions
AT romanenkomg modificationofentropybasedalgorithmfordeterminingwordsboundariesinnoisyconditions
AT romanenkomg modificationofentropybasedalgorithmfordeterminingwordsboundariesinnoisyconditions
_version_ 1760601493836136448