Skip to main content
EXTENDED SEARCH
Log in
Top
Published in:
Read chapter Read first chapter

2021 | OriginalPaper | Chapter

DNN-Based Semantic Rescoring Models for Speech Recognition

Authors : Irina Illina, Dominique Fohr

Published in: Text, Speech, and Dialogue

Publisher: Springer International Publishing

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

The chapter delves into the application of deep neural network-based semantic rescoring models for speech recognition, aiming to improve accuracy by incorporating semantic information. It discusses the integration of semantic frames and target words in recurrent neural network language models and the use of transformer LMs trained with techniques like subword units and adaptive softmax. The authors propose two rescoring approaches: a word2vec-based model and a BERT-based model, each designed to reevaluate the ASR N-best list using semantic representations. Experimental results demonstrate the effectiveness of these models in reducing word error rates, particularly in noisy environments. The study highlights the potential of advanced language models and deep learning techniques in enhancing speech recognition systems.
AI Generated

This summary of the content was generated with the help of AI.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Business + Economics & Engineering + Technology"

Online-Abonnement

Springer Professional "Business + Economics & Engineering + Technology" gives you access to:

  • more than 102.000 books
  • more than 537 journals

from the following subject areas:

  • Automotive
  • Construction + Real Estate
  • Business IT + Informatics
  • Electrical Engineering + Electronics
  • Energy + Sustainability
  • Finance + Banking
  • Management + Leadership
  • Marketing + Sales
  • Mechanical Engineering + Materials
  • Insurance + Risk


Secure your knowledge advantage now!

inform now

Springer Professional "Engineering + Technology"

Online-Abonnement

Springer Professional "Engineering + Technology" gives you access to:

  • more than 67.000 books
  • more than 390 journals

from the following specialised fileds:

  • Automotive
  • Business IT + Informatics
  • Construction + Real Estate
  • Electrical Engineering + Electronics
  • Energy + Sustainability
  • Mechanical Engineering + Materials





 

Secure your knowledge advantage now!

inform now

Springer Professional "Business + Economics"

Online-Abonnement

Springer Professional "Business + Economics" gives you access to:

  • more than 67.000 books
  • more than 340 journals

from the following specialised fileds:

  • Construction + Real Estate
  • Business IT + Informatics
  • Finance + Banking
  • Management + Leadership
  • Marketing + Sales
  • Insurance + Risk



Secure your knowledge advantage now!

inform now
previous chapter Leveraging Inter-step Dependencies for Information Extraction from Procedural Task Instructions
next chapter Identification of Scandinavian Languages from Speech Using Bottleneck Features and X-Vectors
Literature
This content is only visible if you are logged in and have the appropriate permissions.
Metadata
Title
DNN-Based Semantic Rescoring Models for Speech Recognition
Authors
Irina Illina
Dominique Fohr
Copyright Year
2021
Book
Text, Speech, and Dialogue

Print ISBN: 978-3-030-83526-2

Electronic ISBN: 978-3-030-83527-9

Copyright Year: 2021

DOI
https://doi.org/10.1007/978-3-030-83527-9_30

Premium Partner

    Image Credits