Change search
ReferencesLink to record
Permanent link

Direct link
Achieving Automatic Speech Recognition for Swedish using the Kaldi toolkit
KTH, School of Computer Science and Communication (CSC).
2016 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Automatisk taligenkänning på svenska med verktyget Kaldi (Swedish)
Abstract [en]

The meager offering of online commercial Swedish Automatic Speech Recognition ser-vices prompts the effort to develop a speech recognizer for Swedish using the open sourcetoolkit Kaldi and publicly available NST speech corpus. Using a previous Kaldi recipeseveral GMM-HMM models are trained and evaluated against commercial options toallow for reasoning of the performance of a customized solution for Automatic SpeechRecognition to that of commercial services. The evaluation takes both accuracy andcomputational speed into consideration. Initial results of the evaluation indicate a sys-tematic bias in the selected test set confirmed by a follow up investigative evaluation.The conclusion is that building a speech recognizer for Swedish using the NST corpusand Kaldi without expert knowledge is feasible but requires further work.

Abstract [sv]

En taligenkännare för svenska utvecklas med målet att utvärdera hur en taligenkännareutvecklad med fritt tillgängliga verktyg står sig mot kommersiella taligenkänningstjänster.Verktyget som används är det öppna källkodsverktyget Kaldi och som träningsdataanvänds det offentligt tillgängliga talkorpuset för svenska från NST. De framtagna mod-ellerna jämförs mot kommersielt tillgängliga tjänster för taligenkänning på svenska.Tidiga resultat i jämförelsen indikerar ett systemiskt jäv i den valda testdata, vilketbekräftas av en uppföljande undersökande utvärdering. Slutsatsen av arbetet är attutsikterna att ta fram en taligenkännare för svenska är goda men kräver omfattandearbete.

Place, publisher, year, edition, pages
2016. , 47 p.
Keyword [en]
ASR, Kaldi, NST, GMM-HMM
National Category
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-194178OAI: oai:DiVA.org:kth-194178DiVA: diva2:1038763
External cooperation
Omnitor AB
Subject / course
Computer Science
Educational program
Master of Science - Computer Science
Presentation
2016-08-19, Fantum, Lindstedtsvägen 24, Stockholm, 15:00 (English)
Supervisors
Examiners
Available from: 2016-10-31 Created: 2016-10-18 Last updated: 2016-10-31Bibliographically approved

Open Access in DiVA

fulltext(772 kB)12 downloads
File information
File name FULLTEXT01.pdfFile size 772 kBChecksum SHA-512
80771634d9619952082ab5cecd65d0abf7ab1f024c9d20c9097c305f75dfb7ee94c6a07921f042cf4659352cecac172b2ad443620b670b0aefab133e83246307
Type fulltextMimetype application/pdf

By organisation
School of Computer Science and Communication (CSC)
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 12 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

Total: 26 hits
ReferencesLink to record
Permanent link

Direct link