Constructing sub-word units for spoken term detection
Loading...
Date
Authors
van Heerden, Charl
Karakos, Damianos
Narasimhan, Karthik
Schwartz, Richard
Davel, Marelie H.
Journal Title
Journal ISSN
Volume Title
Publisher
Acoustics, Speech and Signal Processing (ICASSP)
Abstract
Spoken term detection, especially of out-of-vocabulary (OOV) keywords,
benefits from the use of sub-word systems. We experiment
with different language-independent 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.
Index Terms— Spoken term detection, BABEL, sub-words,
syllables, morphemes.
Description
Keywords
Citation
Charl van Heerden, Damianos Karakos, Karthik Narasimhan, Marelie Davel and Richard Schwartz, “Constructing sub-word units for spoken term detection”, in Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), pp 5780-5784, New Orleans, Louisiana, 2017. [http://engineering.nwu.ac.za/multilingual-speech-technologies-must/publications]