TY - CHAP A1 - Maas, Roland A1 - Thippur, Akshaya A1 - Sehr, Armin A1 - Kellermann, Walter T1 - An uncertainty decoding approach to noise- and reverberation-robust speech recognition T2 - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 26-31 May 2013, Vancouver, BC, Canada : Proceedings N2 - The generic REMOS (REverberation MOdeling for robust Speech recognition) concept is extended in this contribution to cope with additional noise components. REMOS originally embeds an explicit reverberation model into a hiddenMarkov model (HMM) leading to a relaxed conditional independence assumption for the observed feature vectors. During recognition, a nonlinear optimization problem is to be solved in order to adapt the HMMs' output probability density functions to the current reverberation conditions. The extension for additional noise components necessitates a modified numerical solver for the nonlinear optimization problem. We propose an approximation scheme based on continuous piecewise linear regression. Connected-digit recognition experiments demonstrate the potential of REMOS in reverberant and noisy environments. They furthermore reveal that the benefit of an explicit reverberation model, overcoming the conditional independence assumption, increases with increasing signal-to-noise-ratios. KW - Hidden Markov models KW - Reverberation KW - Noise KW - Speech KW - Adaptation models KW - Vectors KW - Optimization Y1 - 2013 U6 - https://doi.org/10.1109/ICASSP.2013.6639098 SP - 7388 EP - 7392 PB - IEEE ER -