Simplified system for isolated word recognition

This paper presents a general-purpose system for recognition of a limited set of words uttered in isolation. Such a system is intended for voice control of robot's movements. In order to minimize the number of operations performed during the recognition process and to limit the memory requireme...

Full description

Saved in:
Bibliographic Details
Main Authors: R. GUBRYNOWICZ, K. MARASEK, W. MIKIEL, W. WIĘŹLAK
Format: Article
Language:English
Published: Institute of Fundamental Technological Research Polish Academy of Sciences 2014-05-01
Series:Archives of Acoustics
Online Access:https://acoustics.ippt.pan.pl/index.php/aa/article/view/1289
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849423859304890368
author R. GUBRYNOWICZ
K. MARASEK
W. MIKIEL
W. WIĘŹLAK
author_facet R. GUBRYNOWICZ
K. MARASEK
W. MIKIEL
W. WIĘŹLAK
author_sort R. GUBRYNOWICZ
collection DOAJ
description This paper presents a general-purpose system for recognition of a limited set of words uttered in isolation. Such a system is intended for voice control of robot's movements. In order to minimize the number of operations performed during the recognition process and to limit the memory requirements frequency analysis of the signal was performed in adequately selected bands. Output signals from filters undergo detection and through an A/D converter are introduced into a computer where they undergo further processing logarithmic conversion and linear time standarization, among others. This leads to a reduction of the number range in further calculations. The DTW algorithm was used in the recognition process, while templates of individual words are introduced once, in principle separately for individual operators. The developed system speaker-dependent, in principle was verified experimentally for various vocabularies (containing 20 to 60 words) uttered by 11 voices (including 1 female voice). The average recognition accuracy for a 60 word wocabulary exceeded 98% for individual voices, while in a case of recognition whithout system accomodation to given voice the average error of recognition increased by about 10%.
format Article
id doaj-art-0db4101cde4e475c8c8d20fe595024e9
institution Kabale University
issn 0137-5075
2300-262X
language English
publishDate 2014-05-01
publisher Institute of Fundamental Technological Research Polish Academy of Sciences
record_format Article
series Archives of Acoustics
spelling doaj-art-0db4101cde4e475c8c8d20fe595024e92025-08-20T03:30:25ZengInstitute of Fundamental Technological Research Polish Academy of SciencesArchives of Acoustics0137-50752300-262X2014-05-01153-4Simplified system for isolated word recognitionR. GUBRYNOWICZ0K. MARASEK1W. MIKIEL2W. WIĘŹLAK3Institute of Fundamental Technological Research, Polish Academy of SciencesInstitute of Fundamental Technological Research, Polish Academy of SciencesInstitute of Fundamental Technological Research, Polish Academy of SciencesInstitute of Fundamental Technological Research, Polish Academy of SciencesThis paper presents a general-purpose system for recognition of a limited set of words uttered in isolation. Such a system is intended for voice control of robot's movements. In order to minimize the number of operations performed during the recognition process and to limit the memory requirements frequency analysis of the signal was performed in adequately selected bands. Output signals from filters undergo detection and through an A/D converter are introduced into a computer where they undergo further processing logarithmic conversion and linear time standarization, among others. This leads to a reduction of the number range in further calculations. The DTW algorithm was used in the recognition process, while templates of individual words are introduced once, in principle separately for individual operators. The developed system speaker-dependent, in principle was verified experimentally for various vocabularies (containing 20 to 60 words) uttered by 11 voices (including 1 female voice). The average recognition accuracy for a 60 word wocabulary exceeded 98% for individual voices, while in a case of recognition whithout system accomodation to given voice the average error of recognition increased by about 10%.https://acoustics.ippt.pan.pl/index.php/aa/article/view/1289
spellingShingle R. GUBRYNOWICZ
K. MARASEK
W. MIKIEL
W. WIĘŹLAK
Simplified system for isolated word recognition
Archives of Acoustics
title Simplified system for isolated word recognition
title_full Simplified system for isolated word recognition
title_fullStr Simplified system for isolated word recognition
title_full_unstemmed Simplified system for isolated word recognition
title_short Simplified system for isolated word recognition
title_sort simplified system for isolated word recognition
url https://acoustics.ippt.pan.pl/index.php/aa/article/view/1289
work_keys_str_mv AT rgubrynowicz simplifiedsystemforisolatedwordrecognition
AT kmarasek simplifiedsystemforisolatedwordrecognition
AT wmikiel simplifiedsystemforisolatedwordrecognition
AT wwiezlak simplifiedsystemforisolatedwordrecognition