@conference{276, keywords = {spoken term detection, BABEL, sub-words, syllables, morphemes}, author = {Charl Van Heerden and Damianos Karakos and Karthik Narasimhan and Marelie Davel and Richard Schwartz}, title = {Constructing Sub-Word Units for Spoken Term Detection}, abstract = {Spoken term detection, especially of out-of-vocabulary (OOV) key-words, benefits from the use of sub-word systems. We experiment with different language-dependent approaches to sub-word unit generation, generating both syllable-like and morpheme-like units, and demonstrate how the performance of syllable-like units can be improved by artificially increasing the number of unique units. The effect of unit choice is empirically evaluated using the eight languages from the 2016 IARPA BABEL evaluation.}, year = {2017}, journal = {IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP)}, chapter = {5780-5784}, address = {New Orleans, Louisiana}, isbn = {9781509041176}, doi = {10.1109/ICASSP.2017.7953264}, }