Michael Kleinschmidt
Since October 2003 with German Research Foundation (DFG, Bonn)

---

Academic CV

• 1994 - Physik Vordiplom (BSc physics) at Georg-August-Universität Göttingen
• 1996 - Diploma in Applied Science (Meteorology) at Victoria University of Wellington (New Zealand)
• 1999 - Physik Diplom (MSc physics) at Carl von Ossietzky-Universität Oldenburg
• 2001/2002 - visiting researcher at the International Computer Science Institute (ICSI), Berkeley, CA
• 2002 - Promotion zum Dr. rer. nat. (PhD physics) at Carl von Ossietzky-Universität Oldenburg

---

Research Interests

• Robust Automatic Speech Recognition  [DFG Project ROSE]
• Acoustical Speech Enhancement
• Speech Perception by Machines and Humans

---

My PGP public key can be found here (check fingerprint!)

---

Publications download bibtex file here !

[Theses  Journal  Books  Magazins  Proceedings]
 

 Theses:

• Promotionsschrift / PhD Thesis:

Robust speech recognition based on spectro-temporal processing
Carl von Ossietzky-Universität Oldenburg 2002.
Thesis availabel online at BIS publishing
 
• Diplomarbeit / Masters Thesis:

'Störgeräuschunterdrueckung und gehörgerechte Vorverarbeitung für die automatische Spracherkennung' ('Noise Reduction and Perceptive Preprocessing for Automatic Speech Recognition'),
Carl von Ossietzky-Universität Oldenburg 1999.
 
• Studienarbeit:

'Gekoppelte Nichtlinearitäten beim Ladungstransport in hocheffizienten Silizium-Solarzellen - Analyse von Serien- und Kontaktgitterwiderständen' ('small' Masters thesis about 8 weeks of project work: 'Coupled Non-linear Elements in High-efficiency Silicon Solar Cells- Examination of Series and Grid Resistance'),
Fraunhofer Institute for Solar Energy Systems (Freiburg), Department of Solar Cell Technology 1997.
Abstract (in German)
 
• Diploma Thesis:

'Forecasting of Heavy Rainfall over the Southern Alps, New Zealand, Using Machine Learning Techniques.',
Victoria University of Wellington (New Zealand), Research School of Earth Sciences 1995.
Abstract

Journal articles:

• M. Kleinschmidt and V. Hohmann:

'Sub-band SNR Estimation using Auditory Feature Processing',
Speech Communication vol. 39 nos. 1-2 (2003), pp. 47-64, Special Issue on Speech Processing for Hearing Aids.
Download as pdf  (659 kbyte)
 
• M. Kleinschmidt:

'Methods for Capturing Spectro-temporal Modulations in Automatic Speech Recognition',
Acta Acustica united with Acustica 88 (2002), pp. 416-422.
Download as pdf  (194 kbyte)

 

• M. Kleinschmidt, J. Tchorz and B. Kollmeier:

'Combining Speech Enhancement and Auditory Feature Extraction for Robust Speech Recognition',
Speech Communication vol. 34 nos. 1-2 (2001),  pp. 75-91, Special Issue on Robust ASR.
Download as pdf  (503 kbyte)

Articles in books:

• M. Kleinschmidt, M. Marzinzik and B. Kollmeier:

'Combining Monaural Noise Reduction Algorithms and Perceptive Preprocessing for Robust Speech Recognition',
"Psychophysics, Physiology, and Models of Hearing, edited by T. Dau, V. Hohmann, and B. Kollmeier. World Scientific, Singapore (1999), pp. 267-270".
Abstract, Download als pdf(180 kbyte)

Magazine articles:

• J. Tchorz, M. Kleinschmidt, V. Hohmann und B. Kollmeier:

'Von heiseren Handys bis zum Ohr als Chip',
Einblicke 33, Forschungsmagazin der Carl von Ossietzky Universität Oldenburg, Frühjahr 2001.
Download Article (pdf)       Browse Issue

Radio interview (German):

• NDR1, 4 April 2003, 14Uhr: Automatisch Spracherkennung 
  

Contributions to proceedings

• B. Meyer and M. Kleinschmidt:

'Robust speech recognition based on localized spectro-temporal features',
"Elektronische Sprachsignalverarbeitung ESSV 2003".
Download as pdf (708 kbyte)

• H. Gölzer and M. Kleinschmidt:

'Importance of early and late reflections for automatic speech recognition in reverberant environments',
"Elektronische Sprachsignalverarbeitung ESSV 2003".
Download as pdf (117 kbyte)

• M. Kleinschmidt:

'Localized spectro-temporal features for automatic speech recognition',
Proc. EUROSPEECH / INTERSPEECH 2002, Geneva, pp. 2573-2576 (invited paper)
Download as pdf (176 kbyte)

• J. Nix, M. Kleinschmidt, and V. Hohmann:

'Computational Auditory Scene Analysis by using statistics of high-dimensional
speech dynamics and sound source direction',
Proc. EUROSPEECH / INTERSPEECH 2002, Geneva, pp. 1441-1444.
Download as pdf (104 kbyte)

• H. Gölzer und M. Kleinschmidt:

'Automatische Schätzung wichtiger Nachhallparameter',
"Fortschritte der Akustik - DAGA 2003", DEGA.
Download as pdf (1770 kbyte)

• M. Kleinschmidt:

'Spectro-temporal Gabor Features as a Front End for Automatic Speech Recognition',
Forum Acusticum 2002, Sevilla (invited paper).
Download as pdf  (335 kbyte)
 
• M. Kleinschmidt and D. Gelbart:

'Improving Word Accuracy with Gabor Feature Extraction',
ICSLP 2002, Denver
Download as pdf  (50 kbyte)
 
• Tchorz, J., Kleinschmidt, M., and Kollmeier, B.:

'Noise suppression based on neurophysiologically motivated SNR estimation for robust speech recognition',
Advances in Neural Information Processing Systems 13 - NIPS 2000, pp. 821-827, MIT Press.
Download as pdf (223 kbyte)
 
• M. Kleinschmidt und V. Hohmann:

'Perzeptive Vorverarbeitung und automatische Selektion sekundärer Merkmale zur robusten Spracherkennung',
"Fortschritte der Akustik - DAGA 2000", Oldenburg, pp. 382-383, DEGA, Oldenburg.
HTML,Download as pdf (205 kbyte)
 
• J. Anemüller, M. Kleinschmidt und B. Kollmeier:

'Blinde Quellentrennung als Vorverarbeitung zur robusten Spracherkennung',
"Fortschritte der Akustik - DAGA 2000", Oldenburg, pp. 364-365, DEGA, Oldenburg.
Download as pdf (96 kbyte)
 
• C. Hartmann, M. Kleinschmidt, J. Tchorz und B. Kollmeier:

'Gehörgerechte Vorverarbeitung für die robuste Spracherkennung auf Basis von Wortuntereinheiten',
"Fortschritte der Akustik - DAGA 2000", Oldenburg, pp. 380-381, DEGA, Oldenburg.
 
• Kleinschmidt, M., Wittkop, T., and Kollmeier, B.:

'Evaluation of monaural and binaural speech enhancement for robust auditory-based automatic speech recognition'.
J. Acoust. Soc. Am. 105 (2), p. 977. Joint Meeting ASA/EAA/DEGA, Berlin, Germany, 1999.
 
• Tchorz, J., Kleinschmidt, M., and Kollmeier, B.,

'A psychoacoustical model of the auditory periphery as front end for ASR'.
J. Acoust. Soc. Am. 105 (2), p. 1157. Joint Meeting ASA/EAA/DEGA, Berlin, Germany, 1999. Also on CDROM.
 
• J. Tchorz, M. Kleinschmidt, K. Kasper und B. Kollmeier:

'Auditory Feature Extraction and Recognizer Dependencies',
Proceedings of "Workshop on Robust Methods for Speech Recognition, pp. 67-70, May 25-26, 1999, Tampere, Finland".
Download als pdf (190 kbyte)
 
• M. Kleinschmidt, J. Tchortz, T. Wittkop, V. Hohmann und B. Kollmeier:

'Robuste Spracherkennung durch binaural Richtungsfilterung und gehörgerechte Vorverabeitung',
"Fortschritte der Akustik - DAGA 1998", Zürich, pp. 396-397, DEGA, Oldenburg.
HTML,Download as pdf (160 kbyte)