Support software for Automatic Speech Recognition systems targeted for non-native speech

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Nowadays automatic speech recognition (ASR) systems can achieve higher and higher accuracy rates depending on the methodology applied and datasets used. The rate decreases significantly when the ASR system is being used with a non-native speaker of the language to be recognized. The main reason for this is specific pronunciation and accent features related to the mother tongue of that speaker, which influence the pronunciation. At the same time, an extremely limited volume of labeled non-native speech datasets makes it difficult to train, from the ground up, sufficiently accurate ASR systems for non-native speakers. In this research we address the problem and its influence on the accuracy of ASR systems, using the style transfer methodology. We designed a pipeline for modifying the speech of a non-native speaker so that it more closely resembles the native speech. This paper covers experiments for accent modification using different setups and different approaches, including neural style transfer and autoencoder. The experiments were conducted on English language pronounced by Japanese speakers (UME-ERJ dataset). The results show that there is a significant relative improvement in terms of the speech recognition accuracy. Our methodology reduces the necessity of training new algorithms for non-native speech (thus overcoming the obstacle related to the data scarcity) and can be used as a wrapper for any existing ASR system. The modification can be performed in real time, before a sample is passed into the speech recognition system itself.

Original languageEnglish
Title of host publication22nd International Conference on Information Integration and Web-Based Applications and Services, iiWAS 2020 - Proceedings
EditorsMaria Indrawan-Santiago, Eric Pardede, Ivan Luiz Salvadori, Matthias Steinbauer, Ismail Khalil, Gabriele Kotsis
PublisherAssociation for Computing Machinery
Pages55-61
Number of pages7
ISBN (Electronic)9781450389228
DOIs
Publication statusPublished - 2020 Nov 30
Event22nd International Conference on Information Integration and Web-Based Applications and Services, iiWAS 2020 - Virtual, Online, Thailand
Duration: 2020 Nov 302020 Dec 2

Publication series

NameACM International Conference Proceeding Series

Conference

Conference22nd International Conference on Information Integration and Web-Based Applications and Services, iiWAS 2020
Country/TerritoryThailand
CityVirtual, Online
Period20/11/3020/12/2

Keywords

  • deep learning
  • machine learning
  • neural network
  • non-native speaker
  • speech recognition
  • style transfer

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Support software for Automatic Speech Recognition systems targeted for non-native speech'. Together they form a unique fingerprint.

Cite this