Partitioning of Two-Speaker Conversation Datasets

  title={Partitioning of Two-Speaker Conversation Datasets},
  author={Carlos Vaquero and Alfonso Ortega and Eduardo Lleida},
We address the speaker partitioning problem on datasets composed of two-speaker conversations. In such a situation, it is desirable to obtain a good overall diarization performance but even in that case, the performance of the partitioning problem can be severely degraded if some of the recordings are incorrectly segmented. We show that the performance of a bottom-up speaker clustering approach for the partitioning of two-speaker conversation datasets is sensitive to errors in the diarization… CONTINUE READING