A Category Based Approach for Recognitionof Out - of - Vocabulary

Das diesem Bericht zugrundeliegende Forschungsvorhaben wurde mit Mitteln des Bundesministers f ur Bildung, Wissenschaft, Forschung und Technologie unter dem F orderkennzeichen 01 IV 102 H/0 gef ordert. Die Verantwortung f ur den Inhalt dieser Arbeit liegt bei den Autoren. ABSTRACT In almost all applications of automatic speech recognition, especially in spontaneous speech tasks, the recognizer vocabulary cannot cover all occurring words. There is always a signiicant amount of out-of-vocabulary words even when the vocabulary size is very large. In this paper we present a new approach for the integration of out-of-vocabulary words into statistical language models. We use category information for all words in the training corpus to deene a function that gives an approximation of the out-of-vocabulary word emission probability for each word category. This information is integrated into the language models. Although we use a simple acoustic model for out-of-vocabulary words, we achieve a 6% reduction of word error rate on spontaneous speech data with about 5% out-of-vocabulary rate.