Heikki Kallasjoki
Heikki Kallasjoki
Google UK Ltd
Verified email at
Cited by
Cited by
Weighted linear prediction for speech analysis in noisy conditions
J Pohjalainen, H Kallasjoki, KJ Palomäki, M Kurimo, P Alku
Tenth Annual Conference of the International Speech Communication Association, 2009
Mask estimation and imputation methods for missing data speech recognition in a multisource reverberant environment
S Keronen, H Kallasjoki, U Remes, GJ Brown, JF Gemmeke, KJ Palomäki
Computer Speech & Language 27 (3), 798-819, 2013
Estimating uncertainty to improve exemplar-based feature enhancement for noise robust speech recognition
H Kallasjoki, JF Gemmeke, KJ Palomaki
IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP) 22 (2 …, 2014
Recognition of Reverberant Speech by Missing Data Imputation and NMF Feature Enhancement
H Kallasjoki, JF Gemmeke, KJ Palomäki, AV Beeston, GJ Brown
Proceedings of the REVERB'14 workshop, 2014
Mask estimation and sparse imputation for missing data speech recognition in multisource reverberant environments
H Kallasjoki, S Keronen, GJ Brown, J Gemmeke, U Remes, KJ Palomäki
Proceedings CHiME 2011, 1-6, 2011
Noise robust LVCSR feature extraction based on stabilized weighted linear prediction
H Kallasjoki, K Palomäki, C Magi, P Alku, M Kurimo
Proceedings of the 13th International Conference Speech and Computer (SPECOM …, 2009
Uncertainty measures for improving exemplar-based source separation
H Kallasjoki, U Remes, J Gemmeke, T Virtanen, KJ Palomäki
Proceedings Interspeech 2011, 469-472, 2011
Reverberation robust speech recognition by matching distributions of spectrally and temporally decorrelated features
KJ Palomäki, H Kallasjoki
Proceedings of the REVERB'14 Workshop, 2014
Feature Enhancement and Uncertainty Estimation for Recognition of Noisy and Reverberant Speech
H Kallasjoki
Aalto University, 2016
Feature enhancement of reverberant speech by distribution matching and non-negative matrix factorization
S Keronen, H Kallasjoki, KJ Palomäki, GJ Brown, JF Gemmeke
EURASIP Journal on Advances in Signal Processing 2015 (1), 76, 2015
On the role of missing data imputation and NMF feature enhancement in building synthetic voices using reverberant speech
D Gowda, H Kallasjoki, R Karhila, C Contan, K Palomäki, M Giurgiu, ...
Fifteenth Annual Conference of the International Speech Communication …, 2014
Noise robust missing data mask estimation based on automatically learned features
S Keronen, U Remes, H Kallasjoki, K Palomäki
the 2nd CHiME Workshop on Machine Listening in Multisource Environments, 77-78, 2013
Methods for Spectral Envelope Estimation in Noise Robust Speech Recognition
H Kallasjoki
Master's Thesis, Helsinki University of Technology, 2009
Feature Extraction
H Kallasjoki
Project report, Helsinki University of Technology, 27, 0
The system can't perform the operation now. Try again later.
Articles 1–14