A method and apparatus for identifying a speech signal as representing speechin a given candidate language. First, the described illustrative embodiment performs alanguage-specific phoneme recognition on the speech signal for the given candidatelanguage. Next, a corresponding phonemotactic (i.e., phoneme transition probability)model for the given language is applied to produce one or more corresponding phonemesequences and associated likelihood scores (e.g, probabilities). Then, a correspondinglexical model for the given language is applied to the phoneme sequences and theirassociated likelihood scores. In this manner, the lexical characteristics of the givenlanguage are taken into account in order to identify the most likely phoneme sequence(assuming that the given candidate language is, in fact, the language which was spoken)and its associated likelihood. This associated likelihood is used to provide a resultantlikelihood score for the given candidate language. Finally, the speech signal isidentified as representing speech in the given language based on the resultant likelihoodscore so obtained. In particular, the speech signal is analyzed in accordance with theabove with respect to each of a plurality of candidate languages, and is identified asrepresenting speech in the candidate language which produces the highest likelihoodscore.
展开▼
