Mirko Hannemann
Mirko Hannemann
Speech Researcher, Apple Inc
Verifierad e-postadress på apple.com - Startsida
Titel
Citeras av
Citeras av
År
The Kaldi speech recognition toolkit
D Povey, A Ghoshal, G Boulianne, L Burget, O Glembek, N Goel, ...
IEEE 2011 workshop on automatic speech recognition and understanding, 2011
43062011
Generating exact lattices in the WFST framework
D Povey, M Hannemann, G Boulianne, L Burget, A Ghoshal, M Janda, ...
2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012
1352012
Generating exact lattices in the WFST framework
D Povey, M Hannemann, G Boulianne, L Burget, A Ghoshal, M Janda, ...
2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012
1352012
Semi-supervised training of deep neural networks
K Veselý, M Hannemann, L Burget
2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 267-272, 2013
1162013
Score normalization and system combination for improved keyword spotting
D Karakos, R Schwartz, S Tsakalidis, L Zhang, S Ranjan, T Ng, R Hsiao, ...
2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 210-215, 2013
1002013
Combination of strongly and weakly constrained recognizers for reliable detection of OOVs
L Burget, P Schwarz, P Matejka, M Hannemann, A Rastrow, C White, ...
2008 IEEE International Conference on Acoustics, Speech and Signal …, 2008
722008
BUT BABEL system for spontaneous Cantonese.
M Karafiát, F Grézl, M Hannemann, K Veselý, J Cernocký
Interspeech 13, 2589-2593, 2013
432013
BUT 2014 Babel system: Analysis of adaptation in NN based systems
M Karafiát, F Grézl, K Veselý, M Hannemann, I Szőke, J Černocký
Fifteenth Annual Conference of the International Speech Communication …, 2014
332014
Detection of out-of-vocabulary words in posterior based ASR
H Ketabdar, M Hannemann, H Hermansky
Eighth Annual Conference of the International Speech Communication Association, 2007
302007
But neural network features for spontaneous Vietnamese in BABEL
M Karafiát, F Grézl, M Hannemann, JH Černocký
2014 IEEE International Conference on Acoustics, Speech and Signal …, 2014
222014
Similarity scoring for recognizing repeated out-of-vocabulary words
M Hannemann, S Kombrink, M Karafiát, L Burget
Eleventh Annual Conference of the International Speech Communication Association, 2010
132010
Recovery of rare words in lecture speech
S Kombrink, M Hannemann, L Burget, H Heřmanský
International Conference on Text, Speech and Dialogue, 330-337, 2010
122010
But ASR system for BABEL surprise evaluation 2014
M Karafiát, K Veselý, I Szoke, L Burget, F Grézl, M Hannemann, ...
2014 IEEE Spoken Language Technology Workshop (SLT), 501-506, 2014
92014
Segmental Encoder-Decoder Models for Large Vocabulary Automatic Speech Recognition.
E Beck, M Hannemann, P Doetsch, R Schlüter, H Ney
Interspeech, 766-770, 2018
82018
Out-of-vocabulary word detection and beyond
S Kombrink, M Hannemann, L Burget
Detection and Identification of Rare Audiovisual Cues, 57-65, 2012
72012
Hierarchical HMM-based semantic concept labeling model
KT Mengistu, M Hannemann, T Baum, A Wendemuth
2008 IEEE Spoken Language Technology Workshop, 57-60, 2008
62008
Inverted Alignments for End-to-End Automatic Speech Recognition
PDMHRSH Ney
IEEE Journal of Selected Topics in Signal Processing, 2017
52017
Combining forward and backward search in decoding
M Hannemann, D Povey, G Zweig
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
52013
Connecting and Comparing Language Model Interpolation Techniques
E Pusateri, C Van Gysel, R Botros, S Badaskar, M Hannemann, Y Oualil, ...
arXiv preprint arXiv:1908.09738, 2019
42019
Bayesian joint-sequence models for grapheme-to-phoneme conversion
M Hannemann, J Trmal, L Ondel, S Kesiraju, L Burget
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
42017
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20