Improved modeling of OOV words in spontaneous speech

This paper presents an analysis of the out-of-vocabulary (OOV) word problem and results of experiments in language modeling of OOV words. In particular, we introduce the method of iterative substitution for correcting distortions caused by OOV words in the language model. We evaluate the results on two well known spontaneous speech tasks: Verbmobil and ATIS. We show that perplexity as well as error rate reductions can be achieved using iterative substitution. Further, we present preliminary results in combining newspaper texts with the Verbmobil (spontaneous speech) corpus. We could reduce the perplexity of the Verbmobil test set by augmenting the training corpus with newspaper texts. Preliminary recognition results show only slight improvements in the word accuracy and detection of OOV words.