Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A Semi-Supervised Approach to Automatic Speech Recognition Training For the Icelandic Language
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
En semi-övervakad metod för automatisk språkigenkänning för det isländska språket (Swedish)
Abstract [en]

Recent advances in deep learning have enabled certain systems to approach or even achieve human parity in certain tasks, including automatic speech recognition. These new state-of-the-art speech recognition models are most often dependent on vast amounts of expensive high-quality labeled speech data for supervised training. In this work, we consider ways of leveraging unlabeled data for unsupervised training to reduce this costly data dependency. Six altered models are compared to a baseline sequence-to-sequence speech recognition model under three different low resource conditions. We show that for all three conditions, a semi-supervised approach surpasses the quality of the baseline.

Abstract [sv]

Nya framsteg inom djupinlärning har gjort det möjligt för vissa system att närma sig eller till och med uppnå mänsklig paritet i vissa uppgifter, inklusive automatisk taligenkänning. Dessa nya state-of-the-art-metoder är oftast beroende av stora mängder av dyr, högkvalitativ och märkt data för övervakad träning. I det här arbetet undersöker vi olika sätt att utnyttja omärkt data för oövervakad träning för att minska beroendet av dyr data. Sex modifierade modeller jämförs under låga resursförhållanden med en sekvens-till-sekvens taligenkänningsmodell som baslinje. Vi visar att för alla tre förhållanden överträffar en delvis övervakad träning baslinjens kvalitet.

Place, publisher, year, edition, pages
2019. , p. 103
Series
TRITA-EECS-EX ; 2019:517
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-262685OAI: oai:DiVA.org:kth-262685DiVA, id: diva2:1361968
External cooperation
Reykjavik University
Supervisors
Examiners
Available from: 2019-11-11 Created: 2019-10-17 Last updated: 2019-11-11Bibliographically approved

Open Access in DiVA

fulltext(3715 kB)3 downloads
File information
File name FULLTEXT01.pdfFile size 3715 kBChecksum SHA-512
64050eceddf04d40e2121efe778ccef428b867f754c6a11e1d970e5921f23dac5ad6152665ef22f4c8a76f5fc5001753bb50c8de39e27d4abb776e14e36abdc7
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 3 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 13 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf