Skip to main content

2021 | OriginalPaper | Buchkapitel

Use of Median Timbre Features for Speaker Identification of Whispering Sound

verfasst von : Vijay M. Sardar, Manisha L. Jadhav, Saurabh H. Deshmukh

Erschienen in: Techno-Societal 2020

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Identifying speaker from the whispered voice is difficult task contrasted to neutral as voiced phonations are absent in the whisper. The accomplishment of the speaker identification system for the most part relies on the selection of proper audio features reasonable for the type of database and type of application. This paper examines the various audio features available and emphasizes on the use of selected timbrel features which are sorted by Hybrid Selection Algorithm. The limited number of timbrel features namely MFCC, Roll-off, Brightness, Roughness, and irregularity which are found outperforming when tested on CHAIN database. Likewise, the possibility of using the MEDIAN based features is investigated by analysis. The use of Median timbrel features reported an enhancement in speaker identification accuracy by 2.4% compared to timbrel features only in whisper train-whisper test scenario.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Hourri S, Kharroubi J (2020) A deep learning approach for speaker recognition. Int J Speech Technol Springer 23:123–131 Hourri S, Kharroubi J (2020) A deep learning approach for speaker recognition. Int J Speech Technol Springer 23:123–131
2.
Zurück zum Zitat Jahangir R et al (2020) Text-independent speaker identification through feature fusion and deep neural network. IEEE Access 8:32187–32202CrossRef Jahangir R et al (2020) Text-independent speaker identification through feature fusion and deep neural network. IEEE Access 8:32187–32202CrossRef
3.
Zurück zum Zitat Singh A, Joshi AM (2020) Speaker identification through natural and whisper speech signal. In: Janyani V, Singh G, Tiwari M, d'Alessandro A (eds) Optical and wireless technologies. Lecture Notes in Electrical Engineering, vol 546. Springer, Singapore Singh A, Joshi AM (2020) Speaker identification through natural and whisper speech signal. In: Janyani V, Singh G, Tiwari M, d'Alessandro A (eds) Optical and wireless technologies. Lecture Notes in Electrical Engineering, vol 546. Springer, Singapore
4.
Zurück zum Zitat Fan X, Godin KW, Hansen JHL (2011) Acoustic analysis of whispered speech for phoneme and speaker dependency. In: Proceedings of the annual conference of the international speech communication association, INTERSPEECH, pp 181–184 Fan X, Godin KW, Hansen JHL (2011) Acoustic analysis of whispered speech for phoneme and speaker dependency. In: Proceedings of the annual conference of the international speech communication association, INTERSPEECH, pp 181–184
5.
Zurück zum Zitat Bhattacharjee M, Prasanna SRM, Guha P (2018) Time-frequency audio features for speech-music classification. Project: Broadcast Video Analytics Bhattacharjee M, Prasanna SRM, Guha P (2018) Time-frequency audio features for speech-music classification. Project: Broadcast Video Analytics
6.
Zurück zum Zitat Davis SB, Mermelstein P (1980) Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans Acoust Speech Signal Process ASSP s28:357–366 Davis SB, Mermelstein P (1980) Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans Acoust Speech Signal Process ASSP s28:357–366
7.
Zurück zum Zitat Hermansky H, Malaya N (1998) Spectral basis functions from discriminant analysis. In: International conference on spoken language processing Hermansky H, Malaya N (1998) Spectral basis functions from discriminant analysis. In: International conference on spoken language processing
8.
Zurück zum Zitat Toonen Dekkers RTJ, Aarts RM (1995) On a very low-cost speech-music discriminator. Technical Report 124/95, Nat. Lab. Technical Note Toonen Dekkers RTJ, Aarts RM (1995) On a very low-cost speech-music discriminator. Technical Report 124/95, Nat. Lab. Technical Note
9.
Zurück zum Zitat Dobrowohl FA, Milne AJ, Dean RT (2019) Timbre preferences in the context of mixing music. Appl Sci (2076–3417) 9(8):1695–1695 Dobrowohl FA, Milne AJ, Dean RT (2019) Timbre preferences in the context of mixing music. Appl Sci (2076–3417) 9(8):1695–1695
10.
Zurück zum Zitat Peeters G (2004) A large set of audio features for sound description (similarity and classification) in the CUIDADO project Peeters G (2004) A large set of audio features for sound description (similarity and classification) in the CUIDADO project
11.
Zurück zum Zitat Park TH (2004) Towards automatic musical instrument timbre recognition, PhD thesis, the department of music, Princeton University Park TH (2004) Towards automatic musical instrument timbre recognition, PhD thesis, the department of music, Princeton University
12.
Zurück zum Zitat Albert-Ludwigs-Universität Freiburg (2007) A Matlab Toolbox for Music Information. In: Proceedings of the 31st annual conference of the Gesellschaft für Klassifikation e.V., March 7–9, pp 261–268 Albert-Ludwigs-Universität Freiburg (2007) A Matlab Toolbox for Music Information. In: Proceedings of the 31st annual conference of the Gesellschaft für Klassifikation e.V., March 7–9, pp 261–268
13.
Zurück zum Zitat Lartillot O (2011) MIR toolbox 1.3.3 (Matlab Central Version)—User’s Manual. Finnish centre of excellence in interdisciplinary music research, University of Jyväskylä, Finland Lartillot O (2011) MIR toolbox 1.3.3 (Matlab Central Version)—User’s Manual. Finnish centre of excellence in interdisciplinary music research, University of Jyväskylä, Finland
14.
Zurück zum Zitat Sardar VM, Shirbahadurkar SD (2019) Timbre features for speaker identification of whispering speech: selection of optimal audio descriptors. Int J Comput Appl (Taylor Francis, U.K.). ISSN 1206–212X Sardar VM, Shirbahadurkar SD (2019) Timbre features for speaker identification of whispering speech: selection of optimal audio descriptors. Int J Comput Appl (Taylor Francis, U.K.). ISSN 1206–212X
15.
Zurück zum Zitat Cummins F, Grimaldi M, Leonard T, Simko J (2006) The chains speech corpus: characterizing individual speakers. School of Computer Science and Informatics University College, Dublin Cummins F, Grimaldi M, Leonard T, Simko J (2006) The chains speech corpus: characterizing individual speakers. School of Computer Science and Informatics University College, Dublin
16.
Zurück zum Zitat Deshmukh S, Bhirud SG (2012) A hybrid selection method of audio descriptors for singer identification in North Indian Classical Music. In: Fifth international conference on emerging trends in engineering and technology, pp 224–227 Deshmukh S, Bhirud SG (2012) A hybrid selection method of audio descriptors for singer identification in North Indian Classical Music. In: Fifth international conference on emerging trends in engineering and technology, pp 224–227
17.
Zurück zum Zitat Liu H, Jiang H, Zheng R (2016) Computational and mathematical methods in MedicinePB—Hindawi Publishing Corporation Liu H, Jiang H, Zheng R (2016) Computational and mathematical methods in MedicinePB—Hindawi Publishing Corporation
18.
Zurück zum Zitat Shah JK, Smolenski BY, Yantorno RE, Iyer AN (2015) Sequential k-nearest neighbor pattern recognition for usable speech classification. Signal Processing Conference, IEEE Xplorer Shah JK, Smolenski BY, Yantorno RE, Iyer AN (2015) Sequential k-nearest neighbor pattern recognition for usable speech classification. Signal Processing Conference, IEEE Xplorer
19.
Zurück zum Zitat Sardar VM, Shirbahadurkar SD (2018) Speaker identification of whispering sound: effectiveness of timbral audio descriptors. In: International conference on power, communications and sustainable energy system, Chennai Sardar VM, Shirbahadurkar SD (2018) Speaker identification of whispering sound: effectiveness of timbral audio descriptors. In: International conference on power, communications and sustainable energy system, Chennai
20.
Zurück zum Zitat Wang J-C, Chin Y-H, Hsieh W-C, Lin C-H, Chen Y-R, Siahaan E (2015) Speaker identification with whispered speech for the access control system. IEEE Trans Autom Sci Eng 12:1191–1199CrossRef Wang J-C, Chin Y-H, Hsieh W-C, Lin C-H, Chen Y-R, Siahaan E (2015) Speaker identification with whispered speech for the access control system. IEEE Trans Autom Sci Eng 12:1191–1199CrossRef
Metadaten
Titel
Use of Median Timbre Features for Speaker Identification of Whispering Sound
verfasst von
Vijay M. Sardar
Manisha L. Jadhav
Saurabh H. Deshmukh
Copyright-Jahr
2021
DOI
https://doi.org/10.1007/978-3-030-69921-5_4

    Marktübersichten

    Die im Laufe eines Jahres in der „adhäsion“ veröffentlichten Marktübersichten helfen Anwendern verschiedenster Branchen, sich einen gezielten Überblick über Lieferantenangebote zu verschaffen.