Automatic Compound Word Reconstruction for Speech Recognition of Compounding Languages

@inproceedings{Alum2007AutomaticCW,
  title={Automatic Compound Word Reconstruction for Speech Recognition of Compounding Languages},
  author={Tanel Alum},
  year={2007}
}
This paper compares two approaches to lexical compound word reconstruction from a speech recognizer output where compound words are decomposed. The first method has been proposed earlier and uses a dedicated language model that models compound tails in the context of the preceding words and compound heads only in the context of the tail. A novel approach models imaginable compound particle connectors as hidden events and predicts such events using a simple N-gram language model. Experiments on… CONTINUE READING

Topics from this paper.