N2 - This paper describes a Deep Belief Neural Network (DBNN) and Bidirectional Long-Short Term Memory (LSTM) hybrid used as an acoustic model for Speech Recognition. It was demonstrated by many independent researchers that DBNNs exhibit superior performance to other known machine learning frameworks in terms of speech recognition accuracy. Their superiority comes from the fact that these are deep learning networks. However, a trained DBNN is simply a feed-forward network with no internal memory, unlike Recurrent Neural Networks (RNNs) which are Turing complete and do posses internal memory, thus allowing them to make use of longer context. In this paper, an experiment is performed to make a hybrid of a DBNN with an advanced bidirectional RNN used to process its output. Results show that the use of the new DBNN-BLSTM hybrid as the acoustic model for the Large Vocabulary Continuous Speech Recognition (LVCSR) increases word recognition accuracy. However, the new model has many parameters and in some cases it may suffer performance issues in real-time applications. L1 - http://journals.pan.pl/Content/101382/PDF/05_paper.pdf L2 - http://journals.pan.pl/Content/101382 PY - 2015 IS - No 2 EP - 195 DO - 10.1515/aoa-2015-0021 KW - deep belief neural networks KW - long-short term memory KW - bidirectional recurrent neural networks KW - speech recognition KW - large vocabulary continuous speech recognition A1 - Brocki, Ɓukasz A1 - Marasek, Krzysztof PB - Polish Academy of Sciences, Institute of Fundamental Technological Research, Committee on Acoustics VL - vol. 40 DA - 2015[2015.01.01 AD - 2015.12.31 AD] T1 - Deep Belief Neural Networks and Bidirectional Long-Short Term Memory Hybrid for Speech Recognition SP - 191 UR - http://journals.pan.pl/dlibra/publication/edition/101382 T2 - Archives of Acoustics