Follow
Antti Hurmalainen
Antti Hurmalainen
DSP Algorithm Developer, Yousician
Verified email at tut.fi - Homepage
Title
Cited by
Cited by
Year
Exemplar-based sparse representations for noise robust automatic speech recognition
JF Gemmeke, T Virtanen, A Hurmalainen
IEEE Transactions on Audio, Speech, and Language Processing 19 (7), 2067-2080, 2011
4382011
Non-negative matrix factorization for highly noise-robust asr: To enhance or to recognize?
F Weninger, M Wöllmer, J Geiger, B Schuller, JF Gemmeke, ...
2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012
502012
Group sparsity for speaker identity discrimination in factorisation-based speech recognition
A Hurmalainen, R Saeidi, T Virtanen
Portland, USA:[Sn], 2012
402012
Non-negative matrix deconvolution in noise robust speech recognition
A Hurmalainen, J Gemmeke, T Virtanen
2011 IEEE International Conference on Acoustics, Speech and Signal …, 2011
382011
Modelling non-stationary noise with spectral factorisation in automatic speech recognition
A Hurmalainen, JF Gemmeke, T Virtanen
Computer Speech & Language 27 (3), 763-779, 2013
352013
The TUM+ TUT+ KUL approach to the 2nd CHiME challenge: Multi-stream ASR exploiting BLSTM networks and sparse NMF
JT Geiger, F Weninger, A Hurmalainen, J Gemmeke, M Wöllmer, ...
Proc. 2nd CHiME Speech Separation and Recognition Challenge held in …, 2013
332013
Detection, separation and recognition of speech from continuous signals using spectral factorisation
A Hurmalainen, JF Gemmeke, T Virtanen
2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO …, 2012
322012
Toward a practical implementation of exemplar-based noise robust ASR
JF Gemmeke, A Hurmalainen, T Virtanen, Y Sun
2011 19th European Signal Processing Conference, 1490-1494, 2011
282011
Noise robust speaker recognition with convolutive sparse coding.
A Hurmalainen, R Saeidi, T Virtanen
Interspeech, 244-248, 2015
252015
Exemplar-based speech enhancement and its application to noise-robust automatic speech recognition
JF Gemmeke, T Virtanen, A Hurmalainen
Machine Listening in Multisource Environments, 2011
252011
Exemplar-based sparse representation and sparse discrimination for noise robust speaker identification
R Saeidi, A Hurmalainen, T Virtanen, DA van Leeuwen
Singapore:[Sn], 2012
242012
Exemplar-based recognition of speech in highly variable noise
A Hurmalainen, K Mahkonen, JF Gemmeke, T Virtanen
International Workshop on Machine Listening in Multisource Environments, 1-5, 2011
212011
Similarity induced group sparsity for non-negative matrix factorisation
A Hurmalainen, R Saeidi, T Virtanen
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
122015
Modelling spectro-temporal dynamics in factorisation-based noise-robust automatic speech recognition
A Hurmalainen, T Virtanen
2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012
122012
State-based labelling for a sparse representation of speech and its application to robust speech recognition
T Virtanen, JF Gemmeke, A Hurmalainen
Makuhari, Japan:[Sn], 2010
92010
Compact long context spectral factorisation models for noise robust recognition of medium vocabulary speech
A Hurmalainen, JF Gemmeke, T Virtanen
Proc. CHiME-2013, Vancouver, Canada, 13-18, 2013
82013
HMM-regularization for NMF-based noise robust ASR
J Gemmeke, A Hurmalainen, T Virtanen
Proceedings CHiME 2013, 47-52, 2013
62013
Mapping sparse representation to state likelihoods in noise-robust automatic speech recognition
K Mahkonen, A Hurmalainen, T Virtanen, JF Gemmeke
Twelfth Annual Conference of the International Speech Communication Association, 2011
62011
Learning state labels for sparse classification of speech with matrix deconvolution
A Hurmalainen, T Virtanen
2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 168-173, 2013
52013
Binary non-negative matrix deconvolution for audio dictionary learning
S Drgas, T Virtanen, J Lücke, A Hurmalainen
IEEE/ACM Transactions on Audio, Speech, and Language Processing 25 (8), 1644 …, 2017
42017
The system can't perform the operation now. Try again later.
Articles 1–20