Sami Keronen

Postgraduate researcher, M.Sc. (Tech)

Contact Information

Office:

Room I320 in the ELEC Building,
Otakaari 5 A, 02150 Espoo

Mail address:

Aalto University, School of Electrical Engineering,
Department of Signal Processing and Acoustics,
P.O. Box 13000, FI-00076 AALTO, FINLAND

Email:

sami.(at) .poistatama.fi

Publications

Selected recent publications:
• Keronen S., Remes U., Kallasjoki H., and Palomäki K. J. Noise robust missing data mask estimation based on automatically learned features. CHiME, 2013.
• Keronen S., Cho K., Raiko T., Ilin A., and Palomäki K. J. Gaussian-Bernoulli restricted Boltzmann machines and automatic feature extraction for noise robust missing data mask estimation. In Proc. ICASSP, 2013.
• Turunen V., Kurimo M., and Keronen S. Results for variable speaker and recording conditions on spoken IR in Finnish. In proc. SPECOM 2013.
• Keronen S., Kallasjoki H., Remes U., Brown, G. J., Gemmeke J. F., and Palomäki K. J. Mask estimation and imputation methods for missing data speech recognition in a multisource reverberant environment. Computer Speech and Language, 27:3, 2013.
• Keronen S., Pohjalainen J., Alku P., and Kurimo M. Noise robust LVCSR feature extraction based on extended weighted linear prediction. In Proc. INTERSPEECH, 2011.
• Kallasjoki H., Keronen S, Brown G. J., Gemmeke J. F., Remes U., and Palomäki K. J. Mask estimation and sparse imputation for missing data speech recognition in multisource reverberant environments. CHiME, 2011.
• Keronen S., Remes U., Virtanen T., Palomäki K. J., and Kurimo M. Comparison of noise robust methods in large vocabulary speech recognition. In Proc. EUSIPCO, 2010, pp. 1973-1977.

Thesis

• Parallel model combination in large vocabulary continuous speech recognition. Helsinki University of Technology, 2009.

Research

My main research interest is in noise robust automatic speech recognition and I am member of the Speech Recognition Group.