A neural network based language identification system is described, which uses language independent phoneme clusters as speech units to recognize the language spoken by native speakers over the telephone. We extend our previous work comparing phoneme-cluster and phoneme based approaches to language identification [l]. By creating a new speech unit valid across all languages in a theoretically motivated manner, we circumvent problems that are associated with fine phone-mic modelling such as high complexity , extensive training requirements , and the linguistically arbitrary reduction to subsets of phonemes . A common set of speech units across languages allows us to automatically derive discriminating sequences of any length and theoretically estimate the language identification error. We demonstrate our implemented system for German vs. English on the OGI-TS database.
Bibliographic reference. Berkling, Kay M. / Barnard, Etienne (1995): "Theoretical error prediction for a language identification system using optimal phoneme clustering", In EUROSPEECH-1995, 351-354.