ISCA Archive Eurospeech 1997
ISCA Archive Eurospeech 1997

Phonetic-context mapping in language identification

Jiri Navratil, Werner Zühlke

This paper deals with the problem of exploiting information from a wide phonetic context for the purpose of language identiffication. Two approaches to language modeling are presented here: 1) modified bigrams with a con- text-mapping matrix and 2) language models based on binary decision trees. Both models were incorporated in a phonotactic language identiffier with a double-bigram decoding architecture and were shown to consistently improve the performance of standard bigrams. Measured on the NIST'95 evaluation set, the described system outperforms the state-of-the-art phonotactic components and is, at the same time, computationally less expensive.

doi: 10.21437/Eurospeech.1997-45

Cite as: Navratil, J., Zühlke, W. (1997) Phonetic-context mapping in language identification. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 71-74, doi: 10.21437/Eurospeech.1997-45

  author={Jiri Navratil and Werner Zühlke},
  title={{Phonetic-context mapping in language identification}},
  booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)},