A study of neural network Russian language models for automatic continuous speech recognition systems


Citar

Texto integral

Acesso aberto Acesso aberto
Acesso é fechado Acesso está concedido
Acesso é fechado Somente assinantes

Resumo

We show the results of studying models of the Russian language constructed with recurrent artificial neural networks for systems of automatic recognition of continuous speech. We construct neural network models with different number of elements in the hidden layer and perform linear interpolation of neural network models with the baseline trigram language model. The resulting models were used at the stage of rescoring the N best list. In our experiments on the recognition of continuous Russian speech with extra-large vocabulary (150 thousands of word forms), the relative reduction in the word error rate obtained after rescoring the 50 best list with the neural network language models interpolated with the trigram model was 14%.

Sobre autores

I. Kipyatkova

St. Petersburg Institute for Informatics and Automation; State University of Aerospace Instrumentation

Autor responsável pela correspondência
Email: kipyatkova@iias.spb.su
Rússia, St. Petersburg; St. Petersburg

A. Karpov

St. Petersburg Institute for Informatics and Automation

Email: kipyatkova@iias.spb.su
Rússia, St. Petersburg

Arquivos suplementares

Arquivos suplementares
Ação
1. JATS XML

Declaração de direitos autorais © Pleiades Publishing, Ltd., 2017