An Objective Parameter to Classify Voice Signals Based on Variation in Energy Distribution
The purpose of this paper is to introduce an iterative nonlinear weighted method based on the variation in spectral energy distribution present in a voice signal to differentiate between four voice types: type 1 voice signals are nearly periodic, type 2 voice signals have strong modulations and subh...
Gespeichert in:
| Veröffentlicht in: | Journal of voice 2019-09, Vol.33 (5), p.591-602 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 602 |
|---|---|
| container_issue | 5 |
| container_start_page | 591 |
| container_title | Journal of voice |
| container_volume | 33 |
| creator | Liu, Boquan Polce, Evan Jiang, Jack |
| description | The purpose of this paper is to introduce an iterative nonlinear weighted method based on the variation in spectral energy distribution present in a voice signal to differentiate between four voice types: type 1 voice signals are nearly periodic, type 2 voice signals have strong modulations and subharmonics, type 3 signals are chaotic, and type 4 signals are dominated by stochastic noise.
A total of 135 voice signal samples of the sustained vowel /a/ were obtained from the Disordered Voice Database and then individually categorized into the appropriate voice types based on the classification system described in Sprecher et al (2010). Voice samples were analyzed using the nonlinear methods of spectrum convergence ratio, rate of divergence, and nonlinear energy difference ratio (NEDR) to investigate classifier efficacy.
An iterative nonlinear weighted method based on the derivative of instantaneous frequency and Fourier transformations is applied to calculate spectral energy distributions. The distribution is then used to calculate the NEDR to classify voice signal types.
Statistical analysis revealed that NEDR effectively differentiated between all four voice types (P |
| doi_str_mv | 10.1016/j.jvoice.2018.02.011 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2042749091</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0892199717305702</els_id><sourcerecordid>2042749091</sourcerecordid><originalsourceid>FETCH-LOGICAL-c362t-5852e849891c25f0c61dc95dd9fcdcdf51bd3066fa03a8f277cff9345f4338c73</originalsourceid><addsrcrecordid>eNp9kMtLAzEQxoMoWh__gUiOXnbNYx_JRai1PkCooPbgJaTJpGRpd2uyLfS_N6Xq0dMMM983H_ND6JKSnBJa3TR5s-m8gZwRKnLCckLpARpQUfOsKIU4RAMiJMuolPUJOo2xIYSwtD1GJ0zWopS8GqDPYYsnswZM7zeAX3XQS-gh4L7Do4WO0bstnu5i8Juft3oR8Z2OYHHX4qkOXvc-db7F4xbCfIvvfeyDn61343N05JIBLn7qGfp4GL-PnrKXyePzaPiSGV6xPitFyUAUUkhqWOmIqag1srRWOmONdSWdWU6qymnCtXCsro1zkhelKzgXpuZn6Hp_dxW6rzXEXi19NLBY6Ba6dVSMFKwuJJE0SYu91IQuxgBOrYJf6rBVlKgdVdWoPVW1o6oIU4lqsl39JKxnS7B_pl-MSXC7F0D6c-MhqGg8tAasDwmtsp3_P-Eb9MSKuA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2042749091</pqid></control><display><type>article</type><title>An Objective Parameter to Classify Voice Signals Based on Variation in Energy Distribution</title><source>MEDLINE</source><source>Elsevier ScienceDirect Journals</source><creator>Liu, Boquan ; Polce, Evan ; Jiang, Jack</creator><creatorcontrib>Liu, Boquan ; Polce, Evan ; Jiang, Jack</creatorcontrib><description>The purpose of this paper is to introduce an iterative nonlinear weighted method based on the variation in spectral energy distribution present in a voice signal to differentiate between four voice types: type 1 voice signals are nearly periodic, type 2 voice signals have strong modulations and subharmonics, type 3 signals are chaotic, and type 4 signals are dominated by stochastic noise.
A total of 135 voice signal samples of the sustained vowel /a/ were obtained from the Disordered Voice Database and then individually categorized into the appropriate voice types based on the classification system described in Sprecher et al (2010). Voice samples were analyzed using the nonlinear methods of spectrum convergence ratio, rate of divergence, and nonlinear energy difference ratio (NEDR) to investigate classifier efficacy.
An iterative nonlinear weighted method based on the derivative of instantaneous frequency and Fourier transformations is applied to calculate spectral energy distributions. The distribution is then used to calculate the NEDR to classify voice signal types.
Statistical analysis revealed that NEDR effectively differentiated between all four voice types (P < 0.001). Subsequent multiclass receiver operating characteristic analysis demonstrated that NEDR (area under the curve [95% CI] = 0.99 [0.96–1.0]) possessed the greatest classification accuracy relative to spectrum convergence ratio and rate of divergence.
NEDR was shown to be an effective metric for objective differentiation between all four voice signal types. NEDR calculations occurred approximately instantaneously, constituting a substantial improvement over the tedious computational time required for calculation of previous nonlinear parameters. This metric could assist clinicians in the diagnosis of voice disorders and monitor the efficacy of treatment through observation of voice acoustical improvement over time.</description><identifier>ISSN: 0892-1997</identifier><identifier>EISSN: 1873-4588</identifier><identifier>DOI: 10.1016/j.jvoice.2018.02.011</identifier><identifier>PMID: 29785936</identifier><language>eng</language><publisher>United States: Elsevier Inc</publisher><subject>Acoustics ; Adolescent ; Adult ; Aged ; Aged, 80 and over ; Chaos ; Databases, Factual ; Derivative of instantaneous frequency ; Female ; Humans ; Male ; Middle Aged ; Nonlinear Dynamics ; Nonlinear energy difference ratio ; Nonlinear weighted ; Phonation ; Signal Processing, Computer-Assisted ; Sound Spectrography ; Speech Acoustics ; Speech Production Measurement ; Voice Quality ; Voice signal classification ; Young Adult</subject><ispartof>Journal of voice, 2019-09, Vol.33 (5), p.591-602</ispartof><rights>2018 The Voice Foundation</rights><rights>Copyright © 2018 The Voice Foundation. Published by Elsevier Inc. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c362t-5852e849891c25f0c61dc95dd9fcdcdf51bd3066fa03a8f277cff9345f4338c73</citedby><cites>FETCH-LOGICAL-c362t-5852e849891c25f0c61dc95dd9fcdcdf51bd3066fa03a8f277cff9345f4338c73</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S0892199717305702$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3537,27901,27902,65534</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/29785936$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Liu, Boquan</creatorcontrib><creatorcontrib>Polce, Evan</creatorcontrib><creatorcontrib>Jiang, Jack</creatorcontrib><title>An Objective Parameter to Classify Voice Signals Based on Variation in Energy Distribution</title><title>Journal of voice</title><addtitle>J Voice</addtitle><description>The purpose of this paper is to introduce an iterative nonlinear weighted method based on the variation in spectral energy distribution present in a voice signal to differentiate between four voice types: type 1 voice signals are nearly periodic, type 2 voice signals have strong modulations and subharmonics, type 3 signals are chaotic, and type 4 signals are dominated by stochastic noise.
A total of 135 voice signal samples of the sustained vowel /a/ were obtained from the Disordered Voice Database and then individually categorized into the appropriate voice types based on the classification system described in Sprecher et al (2010). Voice samples were analyzed using the nonlinear methods of spectrum convergence ratio, rate of divergence, and nonlinear energy difference ratio (NEDR) to investigate classifier efficacy.
An iterative nonlinear weighted method based on the derivative of instantaneous frequency and Fourier transformations is applied to calculate spectral energy distributions. The distribution is then used to calculate the NEDR to classify voice signal types.
Statistical analysis revealed that NEDR effectively differentiated between all four voice types (P < 0.001). Subsequent multiclass receiver operating characteristic analysis demonstrated that NEDR (area under the curve [95% CI] = 0.99 [0.96–1.0]) possessed the greatest classification accuracy relative to spectrum convergence ratio and rate of divergence.
NEDR was shown to be an effective metric for objective differentiation between all four voice signal types. NEDR calculations occurred approximately instantaneously, constituting a substantial improvement over the tedious computational time required for calculation of previous nonlinear parameters. This metric could assist clinicians in the diagnosis of voice disorders and monitor the efficacy of treatment through observation of voice acoustical improvement over time.</description><subject>Acoustics</subject><subject>Adolescent</subject><subject>Adult</subject><subject>Aged</subject><subject>Aged, 80 and over</subject><subject>Chaos</subject><subject>Databases, Factual</subject><subject>Derivative of instantaneous frequency</subject><subject>Female</subject><subject>Humans</subject><subject>Male</subject><subject>Middle Aged</subject><subject>Nonlinear Dynamics</subject><subject>Nonlinear energy difference ratio</subject><subject>Nonlinear weighted</subject><subject>Phonation</subject><subject>Signal Processing, Computer-Assisted</subject><subject>Sound Spectrography</subject><subject>Speech Acoustics</subject><subject>Speech Production Measurement</subject><subject>Voice Quality</subject><subject>Voice signal classification</subject><subject>Young Adult</subject><issn>0892-1997</issn><issn>1873-4588</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp9kMtLAzEQxoMoWh__gUiOXnbNYx_JRai1PkCooPbgJaTJpGRpd2uyLfS_N6Xq0dMMM983H_ND6JKSnBJa3TR5s-m8gZwRKnLCckLpARpQUfOsKIU4RAMiJMuolPUJOo2xIYSwtD1GJ0zWopS8GqDPYYsnswZM7zeAX3XQS-gh4L7Do4WO0bstnu5i8Juft3oR8Z2OYHHX4qkOXvc-db7F4xbCfIvvfeyDn61343N05JIBLn7qGfp4GL-PnrKXyePzaPiSGV6xPitFyUAUUkhqWOmIqag1srRWOmONdSWdWU6qymnCtXCsro1zkhelKzgXpuZn6Hp_dxW6rzXEXi19NLBY6Ba6dVSMFKwuJJE0SYu91IQuxgBOrYJf6rBVlKgdVdWoPVW1o6oIU4lqsl39JKxnS7B_pl-MSXC7F0D6c-MhqGg8tAasDwmtsp3_P-Eb9MSKuA</recordid><startdate>201909</startdate><enddate>201909</enddate><creator>Liu, Boquan</creator><creator>Polce, Evan</creator><creator>Jiang, Jack</creator><general>Elsevier Inc</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope></search><sort><creationdate>201909</creationdate><title>An Objective Parameter to Classify Voice Signals Based on Variation in Energy Distribution</title><author>Liu, Boquan ; Polce, Evan ; Jiang, Jack</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c362t-5852e849891c25f0c61dc95dd9fcdcdf51bd3066fa03a8f277cff9345f4338c73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Acoustics</topic><topic>Adolescent</topic><topic>Adult</topic><topic>Aged</topic><topic>Aged, 80 and over</topic><topic>Chaos</topic><topic>Databases, Factual</topic><topic>Derivative of instantaneous frequency</topic><topic>Female</topic><topic>Humans</topic><topic>Male</topic><topic>Middle Aged</topic><topic>Nonlinear Dynamics</topic><topic>Nonlinear energy difference ratio</topic><topic>Nonlinear weighted</topic><topic>Phonation</topic><topic>Signal Processing, Computer-Assisted</topic><topic>Sound Spectrography</topic><topic>Speech Acoustics</topic><topic>Speech Production Measurement</topic><topic>Voice Quality</topic><topic>Voice signal classification</topic><topic>Young Adult</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Liu, Boquan</creatorcontrib><creatorcontrib>Polce, Evan</creatorcontrib><creatorcontrib>Jiang, Jack</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Journal of voice</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Liu, Boquan</au><au>Polce, Evan</au><au>Jiang, Jack</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An Objective Parameter to Classify Voice Signals Based on Variation in Energy Distribution</atitle><jtitle>Journal of voice</jtitle><addtitle>J Voice</addtitle><date>2019-09</date><risdate>2019</risdate><volume>33</volume><issue>5</issue><spage>591</spage><epage>602</epage><pages>591-602</pages><issn>0892-1997</issn><eissn>1873-4588</eissn><abstract>The purpose of this paper is to introduce an iterative nonlinear weighted method based on the variation in spectral energy distribution present in a voice signal to differentiate between four voice types: type 1 voice signals are nearly periodic, type 2 voice signals have strong modulations and subharmonics, type 3 signals are chaotic, and type 4 signals are dominated by stochastic noise.
A total of 135 voice signal samples of the sustained vowel /a/ were obtained from the Disordered Voice Database and then individually categorized into the appropriate voice types based on the classification system described in Sprecher et al (2010). Voice samples were analyzed using the nonlinear methods of spectrum convergence ratio, rate of divergence, and nonlinear energy difference ratio (NEDR) to investigate classifier efficacy.
An iterative nonlinear weighted method based on the derivative of instantaneous frequency and Fourier transformations is applied to calculate spectral energy distributions. The distribution is then used to calculate the NEDR to classify voice signal types.
Statistical analysis revealed that NEDR effectively differentiated between all four voice types (P < 0.001). Subsequent multiclass receiver operating characteristic analysis demonstrated that NEDR (area under the curve [95% CI] = 0.99 [0.96–1.0]) possessed the greatest classification accuracy relative to spectrum convergence ratio and rate of divergence.
NEDR was shown to be an effective metric for objective differentiation between all four voice signal types. NEDR calculations occurred approximately instantaneously, constituting a substantial improvement over the tedious computational time required for calculation of previous nonlinear parameters. This metric could assist clinicians in the diagnosis of voice disorders and monitor the efficacy of treatment through observation of voice acoustical improvement over time.</abstract><cop>United States</cop><pub>Elsevier Inc</pub><pmid>29785936</pmid><doi>10.1016/j.jvoice.2018.02.011</doi><tpages>12</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0892-1997 |
| ispartof | Journal of voice, 2019-09, Vol.33 (5), p.591-602 |
| issn | 0892-1997 1873-4588 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2042749091 |
| source | MEDLINE; Elsevier ScienceDirect Journals |
| subjects | Acoustics Adolescent Adult Aged Aged, 80 and over Chaos Databases, Factual Derivative of instantaneous frequency Female Humans Male Middle Aged Nonlinear Dynamics Nonlinear energy difference ratio Nonlinear weighted Phonation Signal Processing, Computer-Assisted Sound Spectrography Speech Acoustics Speech Production Measurement Voice Quality Voice signal classification Young Adult |
| title | An Objective Parameter to Classify Voice Signals Based on Variation in Energy Distribution |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-16T11%3A42%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=An%20Objective%20Parameter%20to%20Classify%20Voice%20Signals%20Based%20on%20Variation%20in%20Energy%20Distribution&rft.jtitle=Journal%20of%20voice&rft.au=Liu,%20Boquan&rft.date=2019-09&rft.volume=33&rft.issue=5&rft.spage=591&rft.epage=602&rft.pages=591-602&rft.issn=0892-1997&rft.eissn=1873-4588&rft_id=info:doi/10.1016/j.jvoice.2018.02.011&rft_dat=%3Cproquest_cross%3E2042749091%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2042749091&rft_id=info:pmid/29785936&rft_els_id=S0892199717305702&rfr_iscdi=true |