THE ALGORITHM FOR DETERMINING WORD BOUNDARIES IN CONTINUOUS SPEECH IN TERMS OF NOISE POLLUTION BASED ON THE ANALYSIS OF THE ENTROPY OF THE SPEECH SIGNAL

Automatic speech recognition, especially in noisy environments, is a complex task. The most important stage of automatic speech recognition is the correct definition of word boundaries in the speech stream. Even a slight improvement at the stage of highlighting the boundaries of words, significantly...

Full description

Saved in:
Bibliographic Details
Main Authors: Andrey Sergeyevich Karpov, Galina Vyacheslavovna Shagrova, Victoria Igorevna Drozdova
Format: Article
Language:Russian
Published: North-Caucasus Federal University 2022-10-01
Series:Современная наука и инновации
Subjects:
Online Access:https://msi.elpub.ru/jour/article/view/641
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1839590780484714496
author Andrey Sergeyevich Karpov
Galina Vyacheslavovna Shagrova
Victoria Igorevna Drozdova
author_facet Andrey Sergeyevich Karpov
Galina Vyacheslavovna Shagrova
Victoria Igorevna Drozdova
author_sort Andrey Sergeyevich Karpov
collection DOAJ
description Automatic speech recognition, especially in noisy environments, is a complex task. The most important stage of automatic speech recognition is the correct definition of word boundaries in the speech stream. Even a slight improvement at the stage of highlighting the boundaries of words, significantly affects the operation of the entire speech recognition system. To recognize isolated words, this problem boils down to determining the correct word boundary. For continuous speech, this task is much more difficult, since the speech signal is a continuous stream without any speech pauses. The most promising approach involves the use of speech signal entropy to search for word boundaries.
format Article
id doaj-art-dd4d3c6d3204454ebaa49fb65ce788bd
institution Matheson Library
issn 2307-910X
language Russian
publishDate 2022-10-01
publisher North-Caucasus Federal University
record_format Article
series Современная наука и инновации
spelling doaj-art-dd4d3c6d3204454ebaa49fb65ce788bd2025-08-03T13:08:11ZrusNorth-Caucasus Federal UniversityСовременная наука и инновации2307-910X2022-10-0104889310.33236/2307-910Х-2018-4-24-88-93640THE ALGORITHM FOR DETERMINING WORD BOUNDARIES IN CONTINUOUS SPEECH IN TERMS OF NOISE POLLUTION BASED ON THE ANALYSIS OF THE ENTROPY OF THE SPEECH SIGNALAndrey Sergeyevich Karpov0Galina Vyacheslavovna Shagrova1Victoria Igorevna Drozdova2North - Caucasus Federal UniversityNorth - Caucasus Federal UniversityNorth - Caucasus Federal UniversityAutomatic speech recognition, especially in noisy environments, is a complex task. The most important stage of automatic speech recognition is the correct definition of word boundaries in the speech stream. Even a slight improvement at the stage of highlighting the boundaries of words, significantly affects the operation of the entire speech recognition system. To recognize isolated words, this problem boils down to determining the correct word boundary. For continuous speech, this task is much more difficult, since the speech signal is a continuous stream without any speech pauses. The most promising approach involves the use of speech signal entropy to search for word boundaries.https://msi.elpub.ru/jour/article/view/641энтропияраспознавание границ словслитная речьфреймпорог энтропиизашумление речевого сигналаentropyword boundary recognitioncontinuous speechframeentropy thresholdspeech signal noise
spellingShingle Andrey Sergeyevich Karpov
Galina Vyacheslavovna Shagrova
Victoria Igorevna Drozdova
THE ALGORITHM FOR DETERMINING WORD BOUNDARIES IN CONTINUOUS SPEECH IN TERMS OF NOISE POLLUTION BASED ON THE ANALYSIS OF THE ENTROPY OF THE SPEECH SIGNAL
Современная наука и инновации
энтропия
распознавание границ слов
слитная речь
фрейм
порог энтропии
зашумление речевого сигнала
entropy
word boundary recognition
continuous speech
frame
entropy threshold
speech signal noise
title THE ALGORITHM FOR DETERMINING WORD BOUNDARIES IN CONTINUOUS SPEECH IN TERMS OF NOISE POLLUTION BASED ON THE ANALYSIS OF THE ENTROPY OF THE SPEECH SIGNAL
title_full THE ALGORITHM FOR DETERMINING WORD BOUNDARIES IN CONTINUOUS SPEECH IN TERMS OF NOISE POLLUTION BASED ON THE ANALYSIS OF THE ENTROPY OF THE SPEECH SIGNAL
title_fullStr THE ALGORITHM FOR DETERMINING WORD BOUNDARIES IN CONTINUOUS SPEECH IN TERMS OF NOISE POLLUTION BASED ON THE ANALYSIS OF THE ENTROPY OF THE SPEECH SIGNAL
title_full_unstemmed THE ALGORITHM FOR DETERMINING WORD BOUNDARIES IN CONTINUOUS SPEECH IN TERMS OF NOISE POLLUTION BASED ON THE ANALYSIS OF THE ENTROPY OF THE SPEECH SIGNAL
title_short THE ALGORITHM FOR DETERMINING WORD BOUNDARIES IN CONTINUOUS SPEECH IN TERMS OF NOISE POLLUTION BASED ON THE ANALYSIS OF THE ENTROPY OF THE SPEECH SIGNAL
title_sort algorithm for determining word boundaries in continuous speech in terms of noise pollution based on the analysis of the entropy of the speech signal
topic энтропия
распознавание границ слов
слитная речь
фрейм
порог энтропии
зашумление речевого сигнала
entropy
word boundary recognition
continuous speech
frame
entropy threshold
speech signal noise
url https://msi.elpub.ru/jour/article/view/641
work_keys_str_mv AT andreysergeyevichkarpov thealgorithmfordeterminingwordboundariesincontinuousspeechintermsofnoisepollutionbasedontheanalysisoftheentropyofthespeechsignal
AT galinavyacheslavovnashagrova thealgorithmfordeterminingwordboundariesincontinuousspeechintermsofnoisepollutionbasedontheanalysisoftheentropyofthespeechsignal
AT victoriaigorevnadrozdova thealgorithmfordeterminingwordboundariesincontinuousspeechintermsofnoisepollutionbasedontheanalysisoftheentropyofthespeechsignal
AT andreysergeyevichkarpov algorithmfordeterminingwordboundariesincontinuousspeechintermsofnoisepollutionbasedontheanalysisoftheentropyofthespeechsignal
AT galinavyacheslavovnashagrova algorithmfordeterminingwordboundariesincontinuousspeechintermsofnoisepollutionbasedontheanalysisoftheentropyofthespeechsignal
AT victoriaigorevnadrozdova algorithmfordeterminingwordboundariesincontinuousspeechintermsofnoisepollutionbasedontheanalysisoftheentropyofthespeechsignal