Tytuł artykułu

Deep Belief Neural Networks and Bidirectional Long-Short Term Memory Hybrid for Speech Recognition

Tytuł czasopisma

Archives of Acoustics

Rocznik

2015

Wolumin

vol. 40

Numer

No 2

Autorzy

Brocki, Łukasz ; Marasek, Krzysztof

Słowa kluczowe

deep belief neural networks ; long-short term memory ; bidirectional recurrent neural networks ; speech recognition ; large vocabulary continuous speech recognition

Wydział PAN

Nauki Techniczne

Zakres

191-195

Wydawca

Polish Academy of Sciences, Institute of Fundamental Technological Research, Committee on Acoustics

Data

2015[2015.01.01 AD - 2015.12.31 AD]

Typ

Artykuły / Articles

Identyfikator

DOI: 10.1515/aoa-2015-0021 ; ISSN 0137-5075 ; eISSN 2300-262X

Źródło

Archives of Acoustics; 2015; vol. 40; No 2; 191-195

Referencje

HochreiterS (1995), Long Short - Term Memory, Neural Computation, 9, 1735, doi.org/10.1162/neco.1997.9.8.1735 ; HintonG (2006), A fast learning algorithm for deep belief nets, Neural Computation, 18, 1527, doi.org/10.1162/neco.2006.18.7.1527 ; AckleyD (1985), A Learning Algorithm for Boltzmann Machines, Cognitive Science, 9, 147, doi.org/10.1207/s15516709cog0901_7 ; WerbosP (1987), Backpropagation through time : what it does and how to do it, IEEE, 78, 1550, doi.org/10.1109/5.58337 ; RabinerL (1989), A tutorial on hidden markov models and selected applications in speech recognition pp, IEEE, 257, doi.org/10.1109/5.18626 ; LeeA (2001), Julius an open source real - time large vocabulary recognition engine in European Conference on Speech Communication and Technology pp, Proc, 1691.