Application of LSTM Neural Networks in Language Modelling

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F13%3A43921189" target="_blank" >RIV/49777513:23520/13:43921189 - isvavai.cz</a>
Result on the web
<a href="http://link.springer.com/chapter/10.1007%2F978-3-642-40585-3_14#page-1" target="_blank" >http://link.springer.com/chapter/10.1007%2F978-3-642-40585-3_14#page-1</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-642-40585-3_14" target="_blank" >10.1007/978-3-642-40585-3_14</a>

Result language
angličtina
Original language name
Application of LSTM Neural Networks in Language Modelling
Original language description
Artificial neural networks have become state-of-the-art in the task of language modelling on a small corpora. While feed-forward networks are able to take into account only a fixed context length to predict the next word, recurrent neural networks (RNN)can take advantage of all previous words. Due the difficulties in training of RNN, the way could be in using Long Short Term Memory (LSTM) neural network architecture. In this work, we show an application of LSTM network with extensions on a language modelling task with Czech spontaneous phone calls. Experiments show considerable improvements in perplexity and WER on recognition system over n-gram baseline.
Czech name
—
Czech description
—

Project
<a href="/en/project/DF12P01OVV022" target="_blank" >DF12P01OVV022: ASR- and MT-based Access to a Large Archive of Cultural Heritage (AMALACH)</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)