Search system for an audio archive
Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Speed and accuracy of information retrieval is of utmostimportance value in the contemporary world. Multimediadata is usually indexed not according to the content but toseveral keywords that only approximate the content.
The purpose of the study is to explore the possibility ofusing speech recognition algorithms to improve the qualityof human speech audio files retrieval or live media contentanalysis. The project focuses on phonetic algorithms’ abil-ity to compensate for imperfections of speech recognition.
The project has examined several speech recognitiontools, language models and phonetic matching algorithms.The results can be used for further research, developing orimproving commercial products.
Place, publisher, year, edition, pages
IdentifiersURN: urn:nbn:se:kth:diva-164391OAI: oai:DiVA.org:kth-164391DiVA: diva2:805690
Master of Science - Machine Learning
Lagergren, Jens, professor