ISCA Archive ICSLP 2000
ISCA Archive ICSLP 2000

Speaker change detection using minimum message length criterion

Chaojun Liu, Yonghong Yan

Speaker change detection or speaker-based segmentation is useful and important in many applications, such as transcribing broadcast news or telephone conversations. It usually serves as a preliminary step prior to speech/speaker recognition. Among various methods proposed in the literature, Bayesian Information Criterion (BIC) based method has been widely used. In this paper, we propose to use a different criterion, Minimum Message Length criterion (MML), which is also well known in the statistical community, on speaker change detection problems. MML is an information theoretic criterion that aims to minimize the message length for the description of both model parameters and the data. Previous studies by Oliver etc. in the area other than speech, showed that MML might be a better criterion than BIC on segmentation problems. We extended their work and applied MML criterion to speaker change detection problems. Experiments were carried out on two different types of speech data, and so far, comparable results between BIC and MML have been obtained.


Cite as: Liu, C., Yan, Y. (2000) Speaker change detection using minimum message length criterion. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 3, 514-517

@inproceedings{liu00f_icslp,
  author={Chaojun Liu and Yonghong Yan},
  title={{Speaker change detection using minimum message length criterion}},
  year=2000,
  booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
  pages={vol. 3, 514-517}
}