2014 · 36 citations · 15 references
Language StudiesComputer ScienceLinguisticsComputational LinguisticsMorphologyNatural Language ProcessingKeyword ExtractionMorphological AnalysisMorphological ProcessingMorphological SegmentationPhonological SegmentationSpeech RecognitionKeyword SpottingMorpheme IdentificationMorphological UnitsSupervised Morphological SegmentationUnsupervised Morphological Segmentation
We explore the impact of morphological segmentation on keyword spotting (KWS). Despite potential benefits, stateof-the-art KWS systems do not use morphological information. In this paper, we augment a state-of-the-art KWS system with sub-word units derived from supervised and unsupervised morphological segmentations, and compare with phonetic and syllabic segmentations. Our experiments demonstrate that morphemes improve overall performance of KWS systems. Syllabic units, however, rival the performance of morphological units when used in KWS. By combining morphological, phonetic and syllabic segmentations, we demonstrate substantial performance gains.
15
Results of the 2006 Spoken Term Detection Evaluation
Jonathan G. Fiscus, Jerome Ajot, John S. Garofolo et al. · 2006 · 215 citations
Computing, Arabic, Computer Science +16