Solving the problems of normalization of non-standard words in the text of the uzbek language
Boburkhon TuraevMalika AbdullayevaS.S. IbragimovaaТашкентский государственный университет узбекского языка и литературы имени Алишера Навои
2024en
ABI
Annotatsiya
Text normalization is an important component of thetext-to-speech (TTS) system, and the difficulty of text normalizationlies in distinguishing between non-standard words (non-standardwords). In this paper, a taxonomy of non-standard words basedon Uzbek speech has been developed, and a two-stage strategy fordetermining non-standard words has been proposed. The proposedtwo-stage strategy for identifying non-standard words provides anaccuracy of 98.53% in the open test. Experiments show that nonstandardtaxonomy of words provides high initial performance.
Hali tarjima qilinmagan
Identifikatorlar
Iqtiboslar va manbalar
0 ta iqtibos0 ta foydalanilgan manba