A segment-based automatic language identification system

We have developed a four-language automatic language identification sys-tem for high-quality speech. The system uses a neural network-based segmentation algorithm to segment speech into seven broad phonetic cat-egories. Phonetic and prosodic features computed on these categories are then input to a second network that performs the language classification. The system was trained and tested on separate sets of speakers of Ameri-can English, Japanese, Mandarin Chinese and Tamil. It currently performs with an accuracy of 89.5 % on the utterances of the test set.