engleski

Recognition of Croatian Broadcast Speech

In the paper we present some achievements and results of a project in speech recognition of Croatian broadcast speech. We present the procedures we have performed in order to obtain a domain specific speech database from broadcast news of national programmes. The speech signal acquisition, transcription and segmentation process is described. Further the speech recognition experiments using monophone and triphone acoustic models and a bigram language model are described. Results of Croatian speech recognition experiments using context-independent and context-dependent acoustic models are presented as well.

peech recognition; speech database; broadcast speech

nije evidentirano