This article is cited in 11 papers

Methods of Information Processing and Management

Variants of deep artificial neural networks for speech recognition systems

I. S. Kipyatkova, A. A. Karpov

Laboratory of Speech and Multimodal Interfaces St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS)

Abstract: This paper presents a survey of basic methods for acoustic and language model development based on artificial neural networks for automatic speech recognition systems. The hybrid and tandem approaches for combination of Hidden Markov Models and artificial neural networks for acoustic modelling are given. The creation of language models using feedforward and recurrent neural networks is described. The survey of researches, conducted in this field, shows that application of artificial neural networks at the stages of both acoustic and language modeling allows decreasing word error rate.

Keywords: automatic speech recognition; neural networks; acoustic models; language models.

UDC: 004.522

DOI: 10.15622/sp.49.5

Bibliographic databases:

•