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


Дәйексөз келтіру

Толық мәтін

Ашық рұқсат Ашық рұқсат
Рұқсат жабық Рұқсат берілді
Рұқсат жабық Тек жазылушылар үшін

Аннотация

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%.

Авторлар туралы

I. Kipyatkova

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

Хат алмасуға жауапты Автор.
Email: kipyatkova@iias.spb.su
Ресей, St. Petersburg; St. Petersburg

A. Karpov

St. Petersburg Institute for Informatics and Automation

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

Қосымша файлдар

Қосымша файлдар
Әрекет
1. JATS XML

© Pleiades Publishing, Ltd., 2017