Usefulness of linear prediction residual for replay attack detection
This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequen...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Singh, Madhusudan [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2019transfer abstract |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
Enthalten in: Editorial Board - 2016, München |
|---|---|
| Übergeordnetes Werk: |
volume:110 ; year:2019 ; pages:0 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.aeue.2019.152837 |
|---|
| Katalog-ID: |
ELV048257834 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV048257834 | ||
| 003 | DE-627 | ||
| 005 | 20230626021517.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 191023s2019 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.aeue.2019.152837 |2 doi | |
| 028 | 5 | 2 | |a GBV00000000000787.pica |
| 035 | |a (DE-627)ELV048257834 | ||
| 035 | |a (ELSEVIER)S1434-8411(18)33073-5 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 610 |q VZ |
| 082 | 0 | 4 | |a 370 |q VZ |
| 100 | 1 | |a Singh, Madhusudan |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Usefulness of linear prediction residual for replay attack detection |
| 264 | 1 | |c 2019transfer abstract | |
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a nicht spezifiziert |b z |2 rdamedia | ||
| 338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
| 520 | |a This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. | ||
| 520 | |a This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. | ||
| 650 | 7 | |a Automatic speaker verification (ASV) |2 Elsevier | |
| 650 | 7 | |a EER |2 Elsevier | |
| 650 | 7 | |a t-DCF |2 Elsevier | |
| 650 | 7 | |a Replay detection |2 Elsevier | |
| 650 | 7 | |a Excitation source |2 Elsevier | |
| 700 | 1 | |a Pati, Debadatta |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |n Elsevier |t Editorial Board |d 2016 |g München |w (DE-627)ELV019902425 |
| 773 | 1 | 8 | |g volume:110 |g year:2019 |g pages:0 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.aeue.2019.152837 |3 Volltext |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 951 | |a AR | ||
| 952 | |d 110 |j 2019 |h 0 | ||
| author_variant |
m s ms |
|---|---|
| matchkey_str |
singhmadhusudanpatidebadatta:2019----:sflesfierrdcineiulorpa |
| hierarchy_sort_str |
2019transfer abstract |
| publishDate |
2019 |
| allfields |
10.1016/j.aeue.2019.152837 doi GBV00000000000787.pica (DE-627)ELV048257834 (ELSEVIER)S1434-8411(18)33073-5 DE-627 ger DE-627 rakwb eng 610 VZ 370 VZ Singh, Madhusudan verfasserin aut Usefulness of linear prediction residual for replay attack detection 2019transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. Automatic speaker verification (ASV) Elsevier EER Elsevier t-DCF Elsevier Replay detection Elsevier Excitation source Elsevier Pati, Debadatta oth Enthalten in Elsevier Editorial Board 2016 München (DE-627)ELV019902425 volume:110 year:2019 pages:0 https://doi.org/10.1016/j.aeue.2019.152837 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 110 2019 0 |
| spelling |
10.1016/j.aeue.2019.152837 doi GBV00000000000787.pica (DE-627)ELV048257834 (ELSEVIER)S1434-8411(18)33073-5 DE-627 ger DE-627 rakwb eng 610 VZ 370 VZ Singh, Madhusudan verfasserin aut Usefulness of linear prediction residual for replay attack detection 2019transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. Automatic speaker verification (ASV) Elsevier EER Elsevier t-DCF Elsevier Replay detection Elsevier Excitation source Elsevier Pati, Debadatta oth Enthalten in Elsevier Editorial Board 2016 München (DE-627)ELV019902425 volume:110 year:2019 pages:0 https://doi.org/10.1016/j.aeue.2019.152837 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 110 2019 0 |
| allfields_unstemmed |
10.1016/j.aeue.2019.152837 doi GBV00000000000787.pica (DE-627)ELV048257834 (ELSEVIER)S1434-8411(18)33073-5 DE-627 ger DE-627 rakwb eng 610 VZ 370 VZ Singh, Madhusudan verfasserin aut Usefulness of linear prediction residual for replay attack detection 2019transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. Automatic speaker verification (ASV) Elsevier EER Elsevier t-DCF Elsevier Replay detection Elsevier Excitation source Elsevier Pati, Debadatta oth Enthalten in Elsevier Editorial Board 2016 München (DE-627)ELV019902425 volume:110 year:2019 pages:0 https://doi.org/10.1016/j.aeue.2019.152837 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 110 2019 0 |
| allfieldsGer |
10.1016/j.aeue.2019.152837 doi GBV00000000000787.pica (DE-627)ELV048257834 (ELSEVIER)S1434-8411(18)33073-5 DE-627 ger DE-627 rakwb eng 610 VZ 370 VZ Singh, Madhusudan verfasserin aut Usefulness of linear prediction residual for replay attack detection 2019transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. Automatic speaker verification (ASV) Elsevier EER Elsevier t-DCF Elsevier Replay detection Elsevier Excitation source Elsevier Pati, Debadatta oth Enthalten in Elsevier Editorial Board 2016 München (DE-627)ELV019902425 volume:110 year:2019 pages:0 https://doi.org/10.1016/j.aeue.2019.152837 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 110 2019 0 |
| allfieldsSound |
10.1016/j.aeue.2019.152837 doi GBV00000000000787.pica (DE-627)ELV048257834 (ELSEVIER)S1434-8411(18)33073-5 DE-627 ger DE-627 rakwb eng 610 VZ 370 VZ Singh, Madhusudan verfasserin aut Usefulness of linear prediction residual for replay attack detection 2019transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. Automatic speaker verification (ASV) Elsevier EER Elsevier t-DCF Elsevier Replay detection Elsevier Excitation source Elsevier Pati, Debadatta oth Enthalten in Elsevier Editorial Board 2016 München (DE-627)ELV019902425 volume:110 year:2019 pages:0 https://doi.org/10.1016/j.aeue.2019.152837 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 110 2019 0 |
| language |
English |
| source |
Enthalten in Editorial Board München volume:110 year:2019 pages:0 |
| sourceStr |
Enthalten in Editorial Board München volume:110 year:2019 pages:0 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Automatic speaker verification (ASV) EER t-DCF Replay detection Excitation source |
| dewey-raw |
610 |
| isfreeaccess_bool |
false |
| container_title |
Editorial Board |
| authorswithroles_txt_mv |
Singh, Madhusudan @@aut@@ Pati, Debadatta @@oth@@ |
| publishDateDaySort_date |
2019-01-01T00:00:00Z |
| hierarchy_top_id |
ELV019902425 |
| dewey-sort |
3610 |
| id |
ELV048257834 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV048257834</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626021517.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">191023s2019 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.aeue.2019.152837</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">GBV00000000000787.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV048257834</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S1434-8411(18)33073-5</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">370</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Singh, Madhusudan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Usefulness of linear prediction residual for replay attack detection</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2019transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Automatic speaker verification (ASV)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">EER</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">t-DCF</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Replay detection</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Excitation source</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Pati, Debadatta</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier</subfield><subfield code="t">Editorial Board</subfield><subfield code="d">2016</subfield><subfield code="g">München</subfield><subfield code="w">(DE-627)ELV019902425</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:110</subfield><subfield code="g">year:2019</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.aeue.2019.152837</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">110</subfield><subfield code="j">2019</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| author |
Singh, Madhusudan |
| spellingShingle |
Singh, Madhusudan ddc 610 ddc 370 Elsevier Automatic speaker verification (ASV) Elsevier EER Elsevier t-DCF Elsevier Replay detection Elsevier Excitation source Usefulness of linear prediction residual for replay attack detection |
| authorStr |
Singh, Madhusudan |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV019902425 |
| format |
electronic Article |
| dewey-ones |
610 - Medicine & health 370 - Education |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
610 VZ 370 VZ Usefulness of linear prediction residual for replay attack detection Automatic speaker verification (ASV) Elsevier EER Elsevier t-DCF Elsevier Replay detection Elsevier Excitation source Elsevier |
| topic |
ddc 610 ddc 370 Elsevier Automatic speaker verification (ASV) Elsevier EER Elsevier t-DCF Elsevier Replay detection Elsevier Excitation source |
| topic_unstemmed |
ddc 610 ddc 370 Elsevier Automatic speaker verification (ASV) Elsevier EER Elsevier t-DCF Elsevier Replay detection Elsevier Excitation source |
| topic_browse |
ddc 610 ddc 370 Elsevier Automatic speaker verification (ASV) Elsevier EER Elsevier t-DCF Elsevier Replay detection Elsevier Excitation source |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| author2_variant |
d p dp |
| hierarchy_parent_title |
Editorial Board |
| hierarchy_parent_id |
ELV019902425 |
| dewey-tens |
610 - Medicine & health 370 - Education |
| hierarchy_top_title |
Editorial Board |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)ELV019902425 |
| title |
Usefulness of linear prediction residual for replay attack detection |
| ctrlnum |
(DE-627)ELV048257834 (ELSEVIER)S1434-8411(18)33073-5 |
| title_full |
Usefulness of linear prediction residual for replay attack detection |
| author_sort |
Singh, Madhusudan |
| journal |
Editorial Board |
| journalStr |
Editorial Board |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology 300 - Social sciences |
| recordtype |
marc |
| publishDateSort |
2019 |
| contenttype_str_mv |
zzz |
| container_start_page |
0 |
| author_browse |
Singh, Madhusudan |
| container_volume |
110 |
| class |
610 VZ 370 VZ |
| format_se |
Elektronische Aufsätze |
| author-letter |
Singh, Madhusudan |
| doi_str_mv |
10.1016/j.aeue.2019.152837 |
| dewey-full |
610 370 |
| title_sort |
usefulness of linear prediction residual for replay attack detection |
| title_auth |
Usefulness of linear prediction residual for replay attack detection |
| abstract |
This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. |
| abstractGer |
This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. |
| abstract_unstemmed |
This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U |
| title_short |
Usefulness of linear prediction residual for replay attack detection |
| url |
https://doi.org/10.1016/j.aeue.2019.152837 |
| remote_bool |
true |
| author2 |
Pati, Debadatta |
| author2Str |
Pati, Debadatta |
| ppnlink |
ELV019902425 |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth |
| doi_str |
10.1016/j.aeue.2019.152837 |
| up_date |
2024-07-06T18:21:06.818Z |
| _version_ |
1803854877105848320 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV048257834</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626021517.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">191023s2019 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.aeue.2019.152837</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">GBV00000000000787.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV048257834</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S1434-8411(18)33073-5</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">370</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Singh, Madhusudan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Usefulness of linear prediction residual for replay attack detection</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2019transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">This work demonstrates the usefulness of processing linear prediction (LP) residual signal for detecting replay attacks. The playback device having non-flat frequency response modulates the input signal passing through it, resulting spectral distortion in replay signals especially in the low frequency regions (0–300 Hz). In effect, the excitation source information present below 300 Hz gets distorted. The linear prediction (LP) residual signal implicitly contains excitation source information. The excitation source feature, residual mel frequency cepstral coefficients (RMFCC) obtained from the LP residual signal has been proposed for replay detection task. The significance of RMFCC feature has been investigated through Gaussian mixtures model-universal background model (GMM-UBM) ASV experiments and spoof detection experiments using self-developed IITG-MV replay database and standard ASVspoof 2017 database, respectively. For IITG-MV, relative tandem-detection cost function (t-DCF) improvements of 29.78% (male), 7.96% (female) and 24.52% (whole-set) are observed for RMFCC+MFCC combination over MFCC feature. For ASVspoof 2017, relative EER improvements of 37.34% are reported for RMFCC+CQCC combination over CQCC feature. Minimum reported EER is 9.50% for RMFCC+CQCC system. Experimental results shows that the RMFCC feature contains information complementary to MFCC and CQCC features.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Automatic speaker verification (ASV)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">EER</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">t-DCF</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Replay detection</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Excitation source</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Pati, Debadatta</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier</subfield><subfield code="t">Editorial Board</subfield><subfield code="d">2016</subfield><subfield code="g">München</subfield><subfield code="w">(DE-627)ELV019902425</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:110</subfield><subfield code="g">year:2019</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.aeue.2019.152837</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">110</subfield><subfield code="j">2019</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| score |
7.4013834 |