Puheteknologian uudet menetelmät ja sovellukset (PUMS)

New Methods and Applications of Speech Technology
University of Joensuu

Main Page
News
Goals
Technology
Research Group
Partners
Links
Results
 

Season I

PUMS Reports

  • Introduction to PUMS project: PUMS-intro.ppt
  • PUMS Progress Report (2004-01-09): report-2004-01.doc (40 kb, access requires password)
  • Puheteknologian uudet menetelmät ja sovellukset (research seminar slides 2004-02-26, has a lot of overlap with PUMS-Intro.ppt): Seminar-20040226.ppt (1088 kb, last slide added 2004-03-24)
  • Spectral Features for Automatic Text-Independent Speaker Recognition (research seminar slides 2004-02-27, speech about Tomi's licentiate thesis, see below): research_seminar_27_02_2004.ppt (1376 kb)
  • PUMS Progress Report (2004-04-02): PUMS_tilannekatsaus_huhti_04.doc (176 kb, access requires password)
  • Progress 2003-2004 and Future plans 2004- (slides presented at NRC 2004-04-26): progress.ppt and future.ppt (368 kb and 392 kb, access requires password)
  • PUMS Progress Report (2004-06-08): PUMS_tilannekatsaus_kesa_04.doc (248 kb, access requires password)
  • National PUMS Seminar Presentation (2004-10-14): PUMS-20041014-slides.ppt (1456 kb), a slide show presenting the PUMS project results developed during the PUMS project season I in University of Joensuu.

Software

  • Speaker Recognition Library v0.01 (2004-01-09): srlib001.zip (672 kb)
  • Speaker Profiler Draft v0.01 (2004-01-09) profdemo001.zip (664 kb)

Scientific Reports

  • T. Kinnunen, E. Karpov and P. Fränti, "A speaker pruning algorithm for real-time speaker identification", Lecture Notes in Computer Science, vol. 2688, Int. Conf. on Audio- and Video-Based Biometric Person Authentication (AVBPA'03), Guildford, UK, 639-646, June 2003. speakerpruning_avbpa2003.pdf (280 kb)
  • T. Kinnunen, V. Hautamäki and P. Fränti, "On the fusion of dissimilarity-based classifiers for speaker identification", European Conf. on Speech Communication and Technology, (Eurospeech'2003), Geneva, Switzerland, 2641-2644, September 2003. fusion_eurospeech_2003.pdf (60 kb)
  • T. Kinnunen, Spectral Features for Automatic Text-Independent Speaker Recognition, Ph.Lic. Thesis, Univ. of Joensuu, Dept. of Computer Science, Feb 2004. 2004_PhLic_Kinnunen_Tomi.pdf (3427 kb)

Season II

PUMS Reports

Scientific Reports

  • T. Kinnunen, E. Karpov, P. Fränti, "Real-Time Speaker Identification and Verification", IEEE Transactions on Audio, Speech and Language Processing, 14 (1), pp. 277-288, January 2006.
  • J. Saastamoinen, E. Karpov, V. Hautamäki and P. Fränti, "Accuracy of MFCC based speaker recognition in Series 60 device", EURASIP Journal on Applied Signal Processing, 2005:17 (2005) 2816-2827.
  • J. Saastamoinen, E. Karpov, V. Hautamäki, P. Fränti, "Automatic Speaker Recognition for Series 60 Mobile Devices", Proc. 9th International Conference Speech and Computer (SPECOM'2004), pp. 353-360, St. Petersburg, Russia, September 20-22, 2004. Downloads: PDF (1072 kb), Juhani's Specom'2004 presentation slides (1000 kb).
  • T. Kinnunen, V. Hautamäki, P. Fränti, "Fusion of Spectral Feature Sets for Accurate Speaker Identification", Proc. 9th International Conference Speech and Computer (SPECOM'2004), pp. 361-365, St. Petersburg, Russia, September 20-22, 2004. Downloads: PDF (73 kb)
  • E. Karpov, T. Kinnunen, P. Fränti, "Symmetric Distortion Measure for Speaker Recognition", Proc. 9th International Conference Speech and Computer (SPECOM'2004), pp. 366-370, St. Petersburg, Russia, September 20-22, 2004. Downloads: PDF (88 kb)
  • Kinnunen, T., Karpov, E. and Fränti, P., "Real-Time Speaker Identification", Proc. 8th Int. Conf. on Spoken Language Processing (ICSLP'2004), Vol. III, pp. 1805-1808, Jeju Island, Korea, Oct. 4-8, 2004. Downloads: PDF (368 kb)
  • Kinnunen, T., Karpov, E. and Fränti, P., "Efficient Online Cohort Selection Method for Speaker Verification", Proc. 8th Int. Conf. on Spoken Language Processing (ICSLP'2004), Vol. III, pp. 2401-2402, Jeju Island, Korea, Oct. 4-8, 2004. Downloads: PDF (248 kb)
  • T. Niemi-Laitinen, J. Saastamoinen, T. Kinnunen and P. Fränti, "Applying MFCC-based automatic speaker recognition to GSM and forensic data", The Second Baltic Conference on Human Language Technologies (HLT'2005), pp. 317-322, Tallinn, Estonia, April 2005. Downloads: PDF (184 kb)
  • O. Grebenskaya, "Speaker clustering in speech recognition", MSc thesis, University of Joensuu, March 2005. Download: PDF (668 kb)
  • T. Viinikka, "Puheenkoodauksen vaikutus puhujantunnistukseen", Pro Gradu -tutkielma, tietojenkäsittelytieteen laitos, Joensuun yliopisto, Joulukuu 2004. Download: PDF (388 kb)

Season III

Scientific Reports

  • H. Gupta, V. Hautamaki, T. Kinnunen and P. Fränti "Field Evaluation of Text-Dependent Speaker Recognition in an Access Control Application", Proc. 10th International Conference Speech and Computer (SPECOM'2005), pp. 551-554, Patras, Greece, October 2005. Downloads: PDF (192 kb)
  • T. Kinnunen, R. Gonzalez-Hautamäki, "Long-Term F0 Modeling for Text-Independent Speaker Recognition" Proc. 10th International Conference Speech and Computer (SPECOM'2005), pp. 567-570, Patras, Greece, October 2005. Downloads: PDF (816 kb)
  • J. Saastamoinen, Z. Fiedler, T. Kinnunen, P. Fränti, "On Factors Affecting MFCC-Based Speaker Recognition Accuracy", Proc. 10th International Conference Speech and Computer (SPECOM'2005), pp. 503-506, Patras, Greece, October 2005. Downloads: PDF (40 kb)
  • R. Gonzalez Hautamäki, "Fundamental Frequency Estimation and Modeling for Speaker Recognition", MSc thesis, University of Joensuu, July 2005. Download: PDF (1893 kb)
  • T. Kinnunen, "Optimizing Spectral Feature Based Text-Independent Speaker Recognition", PhD thesis, University of Joensuu, June 2005. Download: PDF (3235 KB)

Season IV

Scientific Reports

  • T. Kinnunen, M. Tuononen and P. Fränti, "Which clustering algorithm to select for text-independent speaker recognition?", Pattern Recognition, (under review)
  • V. Hautamäki, T. Kinnunen, I. Kärkkäinen, J. Saastamoinen, M. Tuononen and P. Fränti, "Maximum a posteriori adaptation of the centroid model for speaker verification", IEEE Signal Processing Letters (accepted)
  • V. Hautamäki, M. Tuononen, T. Niemi-Laitinen and P. Fränti, "Improving speaker verification by periodicity based voice activity detection", Int. Conf. on Speech and Computer (SPECOM07), Moscow, Russia, vol. 2, 645-650, October 2007.
  • T. Kinnunen, E. Chernenko, M. Tuononen, P. Fränti and H. Li, "Voice activity detection using MFCC features and support vector machine", Int. Conf. on Speech and Computer (SPECOM07), Moscow, Russia, vol. 2, 556-561, October 2007.
  • T. Kinnunen, V. Hautamäki and P. Fränti, "On the use of long-term average spectrum in automatic speaker recognition", Int. Symp. on Chinese Spoken Language Processing (ISCSLP06), Singapore, Companion volume, 559-567, December 2006.
  • R. Timofte, V. Hautamäki and P. Fränti, "Speaker, vocabulary and context independent word spotting system in continuous speech", Int. Symp. on Chinese Spoken Language Processing (ISCSLP06), Singapore, Companion volume, 396-407, December 2006.
  • P. Fränti, "Voice activity detection, voice biometric, and keyword search", Puheteknologian jouluseminaari, Tampere, 7-8.12.2006. (PDF)
  • S. Pauk, Use of Long-Term Average Spectrum for Automatic Speaker Recognition, MSc thesis, Univ. of Joensuu, Dept. of Computer Science, Dec 2006. (PDF)
  • Radu Timofte, Short-term time series in automatic speech processing, MSc thesis, Computer Science, University of Joensuu, November 2007. (PDF)
  • P. Fränti, J. Saastamoinen, I. Kärkkäinen, T. Kinnunen, V. Hautamäki, "Implementing Speaker Recognition System: from Matlab to Practice", Research Report A-2007-4, Dept. of Comp. Science, Univ. of Joensuu, Finland, November 2007. (PDF)

Go to beginning of the PUMS main page

Valid HTML 4.01!

This page was last updated 2005-10-18