Modelling unknown words in spontaneous speech

We describe our experiments with different acoustic and language models for unknown words in spontaneous speech. We propose a syllable based approach for the acoustic modelling of new words. Several models of different degrees of complexity are evaluated against each other. We show that the modelling of new words can decrease the error rate in the recognition of spontaneous human-to-human speech. In addition, the new word models can be used as a measure of confidence capable of detecting errors in the recognition of spontaneous speech. Although the best performance is reached by applying phonetic a-priori knowledge in the design of the acoustic models, a pure data-driven approach is proposed which performs only slightly less efficiently.