Trudy SPIIRAN
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Informatics and Automation:
Year:
Volume:
Issue:
Page:
Find






Personal entry:
Login:
Password:
Save password
Enter
Forgotten password?
Register


Trudy SPIIRAN, 2016, Issue 49, Pages 80–103
DOI: https://doi.org/10.15622/sp.49.5
(Mi trspy918)
 

This article is cited in 11 scientific papers (total 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.
Funding agency Grant number
Russian Foundation for Basic Research 15-07-04322_а
15-07-04415_а
Ministry of Education and Science of the Russian Federation МК-5209.2015.8
МД-254.2017.8
Russian Academy of Sciences - Federal Agency for Scientific Organizations 0073-2014-0005
0073-2015-0007
This research is partially supported by the Council for Grants of the President of the Russian Federation (projects No. MK-5209.2015.8 and MD-254.2017.8), by the Russian Foundation for Basic Research (projects No. 15-07-04415 and 15-07-04322), and by state research № 0073-2014-0005 and № 0073-2015-0007.
Bibliographic databases:
Document Type: Article
UDC: 004.522
Language: Russian
Citation: I. S. Kipyatkova, A. A. Karpov, “Variants of deep artificial neural networks for speech recognition systems”, Tr. SPIIRAN, 49 (2016), 80–103
Citation in format AMSBIB
\Bibitem{KipKar16}
\by I.~S.~Kipyatkova, A.~A.~Karpov
\paper Variants of deep artificial neural networks for speech recognition systems
\jour Tr. SPIIRAN
\yr 2016
\vol 49
\pages 80--103
\mathnet{http://mi.mathnet.ru/trspy918}
\crossref{https://doi.org/10.15622/sp.49.5}
\elib{https://elibrary.ru/item.asp?id=27657124}
Linking options:
  • https://www.mathnet.ru/eng/trspy918
  • https://www.mathnet.ru/eng/trspy/v49/p80
  • This publication is cited in the following 11 articles:
    Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Informatics and Automation
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024