A novel weighting technique for fusing Language Identification systems based on pair-wise performances

One of the key research issues in modern language identification (LID) research is how best to combine multiple approaches with different features. Existing statistical fusion techniques are popular but have serious limitations when development data is insufficient, since the data is used for training the statistical fuser. In this paper we compare existing fusion techniques for LID systems and propose an alternative to reduce this problem. By deriving the language-specific weighting directly from pair-wise LID performance, a novel weighting approach is introduced and implemented. Experiments on the NIST LRE 2003 task (CallFriend database) and OGI-TS databases demonstrate that the proposed weighting technique outperforms other recent fusion techniques when the available development data is limited.