Change search
ReferencesLink to record
Permanent link

Direct link
Experiments with artificial neural networks for phoneme and word recognit
KTH, School of Computer Science and Communication (CSC), Speech, Music and Hearing, TMH.
1993 (English)In: STL-QPSR, Vol. 34, no 1, 47-56 p.Article in journal (Refereed) Published
Abstract [en]

An artificial neural network has been bained by the error back-propagation technique to recopse phonemes and words. The speech material was recorded by a male Swedish talker and was labelled by a phonetician. There were 38ou put nodes corresponding to Swedish phonemes. Introducing coarticulation information by adding simple recurrency to the net is shown to be more effective than expanding the size of the input spectral window. The phoneme recognition network was used with dynamic programming for time alignment to recognise connected digits in a speakerindependent way. It was compared to a similar recogniser based on nine quasi-phonetic features instead of 38phonemes. The phoneme-based system performed better fhan the feature-based one for five out of seven speakers.

Place, publisher, year, edition, pages
1993. Vol. 34, no 1, 47-56 p.
National Category
Computer and Information Science
URN: urn:nbn:se:kth:diva-91462OAI: diva2:510361
NR 20140805Available from: 2012-03-15 Created: 2012-03-15Bibliographically approved

Open Access in DiVA

No full text

Search in DiVA

By author/editor
Blomberg, Mats
By organisation
Speech, Music and Hearing, TMH
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
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: 24 hits
ReferencesLink to record
Permanent link

Direct link