@article{SehrBarfussHofmannetal., author = {Sehr, Armin and Barfuss, Hendrik and Hofmann, Christian and Maas, Roland and Kellermann, Walter}, title = {Efficient training of acoustic models for reverberation-robust medium-vocabulary automatic speech recognition}, series = {2014 4th Joint Workshop on Hands-Free Speech Communication and Microphone Arrays, HSCMA, 12-14 May 2014, Villers-les-Nancy, France}, journal = {2014 4th Joint Workshop on Hands-Free Speech Communication and Microphone Arrays, HSCMA, 12-14 May 2014, Villers-les-Nancy, France}, publisher = {IEEE}, doi = {10.1109/HSCMA.2014.6843275}, pages = {177 -- 181}, abstract = {A recently proposed concept for training reverberation-robust acoustic models for automatic speech recognition using pairs of clean and reverberant data is extended from word models to tied-state triphone models in this paper. The key idea of the concept, termed ICEWIND, is to use the clean data for the temporal alignment and the reverberant data for the estimation of the emission densities. Experiments with the 5000-word Wall Street Journal corpus confirm the benefits of ICEWIND with tied-state triphones: While the training time is reduced by more than 90\%, the word accuracy is improved at the same time, both for room-specific and multi-style hidden Markov models. Since the acoustic models trained with ICEWIND need less Gaussian components for the emission densities to achieve comparable recognition rates as Baum-Welch acoustic models, ICEWIND also allows for a reduced decoding complexity.}, language = {en} }