Compound decomposition in dutch large vocabulary speech recognition

This paper addresses compound splitting for Dutch in the context of broadcast news transcription. Language models were created using original text versions and text versions that were decomposed using a data-driven compound splitting algorithm. Language model performances were compared in terms of outof-vocabulary rates and word error rates in a real-world broadcast news transcription task. It was concluded that compound splitting does improve ASR performance. Best results were obtained when frequent compounds were not decomposed.