Show simple item record

dc.contributor.authorDe Vries, Nic J.
dc.contributor.authorBadenhorst, Jaco
dc.contributor.authorBasson, Willem D.
dc.contributor.authorDe Wet, Febe
dc.contributor.authorBarnard, Etienne
dc.contributor.authorDe Waal, Alta
dc.contributor.authorDavel, Marelie H.
dc.date.accessioned2014-09-25T14:25:30Z
dc.date.available2014-09-25T14:25:30Z
dc.date.issued2014
dc.identifier.citationDe Vries, N.J., Davel, M.H. et al. 2014. A smartphone-based ASR data collection tool for under-resourced languages. Speech communications, 56:119-131. [http://www.journals.elsevier.com/speech-communication/]en_US
dc.identifier.issn0038-6308
dc.identifier.issn1573-9672 (O)
dc.identifier.urihttp://hdl.handle.net/10394/11478
dc.description.abstractAcoustic data collection for automatic speech recognition (ASR) purposes is a particularly challenging task when working with under-resourced languages, many of which are found in the developing world. We provide a brief overview of related data collection strategies, highlighting some of the salient issues pertaining to collecting ASR data for under-resourced languages. We then describe the development of a smartphone-based data collection tool, Woefzela, which is designed to function in a developing world context. Specifically, this tool is designed to function without any Internet connectivity, while remaining portable and allowing for the collection of multiple sessions in parallel; it also simplifies the data collection process by providing process support to various role players during the data collection process, and performs on-device quality control in order to maximise the use of recording opportunities. The use of the tool is demonstrated as part of a South African data collection project, during which almost 800 hours of ASR data was collected, often in remote, rural areas, and subsequently used to successfully build acoustic models for eleven languages. The on-device quality control mechanism (referred to as QC-on-the-go) is an interesting aspect of the Woefzela tool and we discuss this functionality in more detail. We experiment with different uses of quality control information, and evaluate the impact of these on ASR accuracy. Woefzela was developed for the Android Operating System and is freely available for use on Android smartphones.en_US
dc.description.urihttp://dx.doi.org/10.1016/j.specom.2013.07.001
dc.description.urihttp://ac.els-cdn.com/S0167639313000915/1-s2.0-S0167639313000915-main.pdf?_tid=50e8344e-4488-11e4-99f1-00000aab0f6c&acdnat=1411631479_28de058d4857dd6edee196bc4922e9aa
dc.description.urihttp://www.sciencedirect.com/science/article/pii/S0167639313000915
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.subjectSmartphone-baseden_US
dc.subjectASR data collectionen_US
dc.subjectUnder-resourced languagesen_US
dc.subjectAutomatic speech recognition (ASR)en_US
dc.subjectASR corporaen_US
dc.subjectSpeech resourcesen_US
dc.subjectSpeech data collectionen_US
dc.subjectBroadband speech corporaen_US
dc.subjectWoefzelaen_US
dc.subjectOn-device quality controlen_US
dc.subjectQC-on-the-goen_US
dc.subjectAndroiden_US
dc.titleA smartphone-based ASR data collection tool for under-resourced languagesen_US
dc.typeArticleen_US
dc.contributor.researchID23607955 - Davel, Marelie Hattingh
dc.contributor.researchID21021287 - Barnard, Etienne


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record