ISCA Archive SLTU 2014
ISCA Archive SLTU 2014

Code-Switching speech recognition for closely related languages

Tetyana Lyudovyk, Valeriy Pylypenko

This work presents an approach to recognition of multispeaker conversational speech with code-switching between Ukrainian and Russian languages. Both inter-sentential and intra-sentential code-switching is handled. The approach takes into account peculiarities of phonetic systems of the closely related Russian and Ukrainian languages. A crosslingual LVCSR system is developed. The acoustic model and pronunciation lexicon are based on Ukrainian phone set. Modeling of pronunciation variation in lexicons helps to cope not only with code-switching speech but also with accented speech. Results of code-switching speech recognition are presented. The approach is suitable especially in cases of intra-sentential code-switching where language identification is problematic.

Index Terms: mixed speech, bilingual speech, codeswitching, Ukrainian, Russian


Cite as: Lyudovyk, T., Pylypenko, V. (2014) Code-Switching speech recognition for closely related languages. Proc. 4th Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU 2014), 188-193

@inproceedings{lyudovyk14_sltu,
  author={Tetyana Lyudovyk and Valeriy Pylypenko},
  title={{Code-Switching speech recognition for closely related languages}},
  year=2014,
  booktitle={Proc. 4th Workshop on Spoken Language Technologies for Under-Resourced Languages  (SLTU 2014)},
  pages={188--193}
}