Automatic Language Identification: Performance vs. Complexity

Automatic Language Identification is the process of classifying an utterance as belonging to one of a number of previously encountered languages. The field has been very active during the last couple of years and has progressed rapidly. We compare two approaches to the problem. The first approach, using hand-labelled speech data has previously been shown to yield better results, but at the price of vastly increased effort needed to label a training corpus. The second approach, not requiring human intervention, trades reduced complexity and effort for performance. Experiments are performed using the OGI Telephone Speech Corpus which contain fine-phonetically labelled utterances in English, German, Japanese, Mandarin, Spanish and Hindi. We present a summary of our research over the last three years, together with insights that we have gained into spoken language processing in general and automatic language identification in particular.