ISCA Archive Eurospeech 1999
ISCA Archive Eurospeech 1999

Fast speaker change detection for broadcast news transcription and indexing

Daben Liu, Francis Kubala

In this paper, we describe a new speaker change detection algorithm designed for fast transcription and audio indexing of spoken broadcast news. We have designed a two-stage algorithm that begins with a gender-independent phone-class recognition pass. We collapse the phoneme inventory to only 4 broad classes and include 4 different models for non-speech, resulting in a small fast decoder that runs in less than 0.1 times real-time. The second stage of the SCD algorithm hypothesizes a speaker change boundary between every phone in the labeled input. The phone level time resolution in our approach permits the algorithm to run quickly while maintaining the same accuracy as a frame level approach. Applying the new algorithms to a large sample of broadcast news programs resulted in improvements in speaker change detection accuracy, speech recognition accuracy, and speed.


doi: 10.21437/Eurospeech.1999-167

Cite as: Liu, D., Kubala, F. (1999) Fast speaker change detection for broadcast news transcription and indexing. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 1031-1034, doi: 10.21437/Eurospeech.1999-167

@inproceedings{liu99_eurospeech,
  author={Daben Liu and Francis Kubala},
  title={{Fast speaker change detection for broadcast news transcription and indexing}},
  year=1999,
  booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
  pages={1031--1034},
  doi={10.21437/Eurospeech.1999-167}
}