GENERAL ENQUIRIES: Tel: + 27 12 841 2911 | Email: callcentre@csir.co.za

Show simple item record

dc.contributor.author Kleynhans, N
dc.contributor.author De Wet, Febe
dc.contributor.author Barnard, E
dc.date.accessioned 2016-07-11T10:58:17Z
dc.date.available 2016-07-11T10:58:17Z
dc.date.issued 2015-11
dc.identifier.citation Kleynhans, N, De Wet, F and Barnard, E. 2015. Unsupervised acoustic model training: comparing South African English and isiZulu. In: Pattern Recognition Association of South Africa and Robotics and Mechatronics International Conference (PRASA-RobMech), Port Elizabeth, South Africa, 25-26 November 2015 en_US
dc.identifier.uri http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7359512&tag=1
dc.identifier.uri http://hdl.handle.net/10204/8629
dc.description Copyright: 2015 by IEEE.Pattern Recognition Association of South Africa and Robotics and Mechatronics International Conference (PRASA-RobMech), Port Elizabeth, South Africa, 25-26 November 2015 en_US
dc.description.abstract Large amounts of untranscribed audio data are generated every day. These audio resources can be used to develop robust acoustic models that can be used in a variety of speech-based systems. Manually transcribing this data is resource intensive and requires funding, time and expertise. Lightly-supervised training techniques, however, provide a means to rapidly transcribe audio, thus reducing the initial resource investment to begin the modelling process. Our findings suggest that the lightly-supervised training technique works well for English but when moving to an agglutinative language, such as isiZulu, the process fails to achieve the performance seen for English. Additionally, phone-based performances are significantly worse when compared to an approach using word-based language models. These results indicate a strong dependence on large or well-matched text resources for lightly-supervised training techniques. en_US
dc.language.iso en en_US
dc.publisher IEEE en_US
dc.relation.ispartofseries Workflow;16006
dc.subject Untranscribed audio data en_US
dc.subject isiZulu en_US
dc.subject Word-based language models en_US
dc.subject Lightly-supervised training en_US
dc.subject Unsupervised training en_US
dc.subject Automatic transcription generation en_US
dc.subject Audio harvesting en_US
dc.subject English language en_US
dc.title Unsupervised acoustic model training: comparing South African English and isiZulu en_US
dc.type Presentation en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search ResearchSpace


Advanced Search

Browse

My Account