ON THE USE OF GRAPHEME MODELS FOR SEARCHING IN LARGE SPOKEN ARCHIVES

Investor logo

Warning

This publication doesn't include Faculty of Education. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

SVEC Jan PSUTKA Josef V. TRMAL Jan SMIDL Lubos IRCING Pavel SEDMIDUBSKÝ Jan

Year of publication 2018
Type Article in Proceedings
Conference 43rd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018)
MU Faculty or unit

Faculty of Informatics

Citation
Doi http://dx.doi.org/10.1109/ICASSP.2018.8461774
Field Informatics
Keywords spoken term detection; speech indexing; grapheme-based speech recognition; keyword search
Description This paper explores the possibility to use grapheme-based word and sub-word models in the task of spoken term detection (STD). The usage of grapheme models eliminates the need for expert-prepared pronunciation lexicons (which are often far from complete) and/or trainable grapheme-to-phoneme (G2P) algorithms that are frequently rather inaccurate, especially for rare words (words coming from a different language). Moreover, the G2P conversion of the search terms that need to be performed on-line can substantially increase the response time of the STD system. Our results show that using various grapheme-based models, we can achieve STD performance (measured in terms of ATWV) comparable with phoneme-based models but without the additional burden of G2P conversion.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.