ISCA Archive Eurospeech 1997
ISCA Archive Eurospeech 1997

Predicting, diagnosing and improving automatic language identification performance

Marc A. Zissman

Language-identification (LID) techniques that use multiple single-language phoneme recognizers followed by n-gram language models have consistently yielded top performance at NIST evaluations. In our study of such systems, we have recently cut our LID error rate by modeling the output of n-gram language models more carefully. Additionally, we are now able to produce meaningful confidence scores along with our LID hypotheses. Finally, we have developed some diagnostic measures that can predict performance of our LID algorithms.


doi: 10.21437/Eurospeech.1997-40

Cite as: Zissman, M.A. (1997) Predicting, diagnosing and improving automatic language identification performance. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 51-54, doi: 10.21437/Eurospeech.1997-40

@inproceedings{zissman97_eurospeech,
  author={Marc A. Zissman},
  title={{Predicting, diagnosing and improving automatic language identification performance}},
  year=1997,
  booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)},
  pages={51--54},
  doi={10.21437/Eurospeech.1997-40},
  issn={1018-4074}
}