@article{291, keywords = {Resource-scarce, Data selection, Corpus design, Speech recognition}, author = {Neil Kleynhans and Etienne Barnard}, title = {Efficient data selection for ASR}, abstract = {Automatic speech recognition (ASR) technology has matured over the past few decades and has made significant impacts in a variety of fields, from assistive technologies to commercial products. However, ASR system development is a resource intensive activity and requires language resources in the form of text annotated audio recordings and pronunciation dictionaries. Unfortunately, many languages found in the developing world fall into the resource-scarce category and due to this resource scarcity the deployment of ASR systems in the developing world is severely inhibited. One approach to assist with resource-scarce ASR system development, is to select 'useful' training samples which could reduce the resources needed to collect new corpora. In this work, we propose a new data selection framework which can be used to design a speech recognition corpus. We show for limited data sets, independent of language and bandwidth, the most effective strategy for data selection is frequency-matched selection and that the widely-used maximum entropy methods generally produced the least promising results. In our model, the frequency-matched selection method corresponds to a logarithmic relationship between accuracy and corpus size; we also investigated other model relationships, and found that a hyperbolic relationship (as suggested from simple asymptotic arguments in learning theory) may lead to somewhat better performance under certain conditions.}, year = {2015}, journal = {Language Resources and Evaluation}, volume = {49}, chapter = {327-353}, publisher = {Springer Science+Business Media }, address = {Dordrecht}, doi = {10.1007/s10579-014-9285-0}, }