Please use this identifier to cite or link to this item:
https://open.uns.ac.rs/handle/123456789/2154
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Galić, Jovan | en_US |
dc.contributor.author | Popović, Branislav | en_US |
dc.contributor.author | Pavlović, Dragana | en_US |
dc.date.accessioned | 2019-09-23T10:19:52Z | - |
dc.date.available | 2019-09-23T10:19:52Z | - |
dc.date.issued | 2018-01-01 | - |
dc.identifier.issn | 17858860 | en_US |
dc.identifier.uri | https://open.uns.ac.rs/handle/123456789/2154 | - |
dc.description.abstract | © 2018, Budapest Tech Polytechnical Institution. All rights reserved. Whisper is a specific mode of speech characterized by turbulent airflow at the glottis level. Despite an increased effort in speech perception, the intelligibility of whisper in human communication is very high. An enormous acoustic mismatch between normally phonated (neutral) and whispered speech is the main reason why modern Automatic Speech Recognition (ASR) systems have significant drop of performances when applied to whisper. In this paper, we present an analysis in recognition of whisper using 2 machine-learning techniques: Hidden Markov Models (HMM) and Support Vector Machines (SVM). The experiments are conducted in both Speaker Dependent (SD) and Speaker Independent (SI) fashion for Whi-Spe speech database. The best neutral-trained whisper recognition accuracy in SD fashion (83.36%) is obtained in SVM framework. At the same time, HMM-based recognition gave the highest recognition accuracy in SI fashion (87.42%). The results in recognition of neutral speech are given as well. | en |
dc.relation.ispartof | Acta Polytechnica Hungarica | en |
dc.title | Whispered speech recognition using hidden markov models and support vector machines | en_US |
dc.type | Journal/Magazine Article | en_US |
dc.identifier.doi | 10.12700/APH.15.5.2018.5.2 | - |
dc.identifier.scopus | 2-s2.0-85056805815 | - |
dc.identifier.url | https://api.elsevier.com/content/abstract/scopus_id/85056805815 | - |
dc.description.version | Unknown | en_US |
dc.relation.lastpage | 29 | en |
dc.relation.firstpage | 11 | en |
dc.relation.issue | 5 | en |
dc.relation.volume | 15 | en |
item.grantfulltext | none | - |
item.fulltext | No Fulltext | - |
crisitem.author.dept | Fakultet tehničkih nauka, Departman za energetiku, elektroniku i telekomunikacije | - |
crisitem.author.parentorg | Fakultet tehničkih nauka | - |
Appears in Collections: | FTN Publikacije/Publications |
SCOPUSTM
Citations
7
checked on Nov 20, 2023
Page view(s)
13
Last Week
9
9
Last month
0
0
checked on May 3, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.