A Multi-Task Approach to Continuous Five-Dimensional Affect Sensing in Natural Speech
ACM Transactions on Interactive Intelligent Systems, Special Issue on Affective Interaction in Natural Environments
2012
2
1
29 pages
Memory-Enhanced Neural Networks and NMF for Robust ASR
Audio, Speech and Language Processing, IEEE/ACM Transactions on
2014
22
6
Jun
1037 - 1046
The TUM+TUT+KUL Approach to the 2nd CHiME Challenge: Multi-Stream ASR Exploiting BLSTM Networks and Sparse NMF
Proc. 2nd CHiME Speech Separation and Recognition Challenge held in conjunction with Proc. Int. Congress on Acoustics Proc. Int. Conf. on Acoustics, Speech, and Signal Processing ICASSP 2013, Vancouver, Canada
winning paper of track 1 and best paper award
IEEE
2013
Feature Enhancement by Deep LSTM Networks for ASR in Reverberant Multisource Environments
Computer Speech and Language, Elsevier
2014
Vol. 28
Jul
pp. 888–902
The Munich Feature Enhancement Approach to the 2013 CHiME Challenge Using BLSTM Recurrent Neural Networks
Proceedings 2nd CHiME Speech Separation and Recognition Challenge held in conjunction with Proc. Int. Congress on Acoustics Proc. Int. Conf. on Acoustics, Speech, and Signal Processing ICASSP 2013, Vancouver, Canada
IEEE
2013
Speaker Trait Characterization in Web Videos: Uniting Speech, Language, and Facial Features
Proceedings 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, Proc. Int. Congress on Acoustics Proc. Int. Conf. on Acoustics, Speech, and Signal Processing ICASSP 2013, Vancouver, Canada
acceptance rate: 53
IEEE
2013
Advances in Emotion Recognition (A. Konar and A. Chakraborty, eds.)
Advances in Emotion Recognition
Wiley-Blackwell
2013
Probabilistic ASR Feature Extraction Applying Context-Sensitive Connectionist Temporal Classification Networks
Proceedings 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, Proc. Int. Congress on Acoustics Proc. Int. Conf. on Acoustics, Speech, and Signal Processing ICASSP 2013, Vancouver, Canada
IEEE
2013
Feature Enhancement by Bidirectional LSTM Networks for Conversational Speech Recognition in Highly Non-Stationary Noise
Proceedings 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, Proc. Int. Congress on Acoustics Proc. Int. Conf. on Acoustics, Speech, and Signal Processing ICASSP 2013, Vancouver, Canada
acceptance rate: 53
IEEE
2013