English

A Statistical Model for Word Discovery in Transcribed Speech

Computation and Language 2007-05-23 v1

Abstract

A statistical model for segmentation and word discovery in continuous speech is presented. An incremental unsupervised learning algorithm to infer word boundaries based on this model is described. Results of empirical tests showing that the algorithm is competitive with other models that have been used for similar tasks are also presented.

Keywords

Cite

@article{arxiv.cs/0111065,
  title  = {A Statistical Model for Word Discovery in Transcribed Speech},
  author = {Anand Venkataraman},
  journal= {arXiv preprint arXiv:cs/0111065},
  year   = {2007}
}

Comments

Expanded version of ICML-01 paper (pp.569--576)