Preprint
Overlap-aware diarization: resegmentation using neural end-to-end overlapped speech detection
Latané Bullock et al., arXiv (submitted to ICASSP 2020), 2019
Read the originalRead on October 17, 2026
- What it is
- A 2019 paper that adds a neural overlapped-speech detector to a speaker diarization system and uses it to assign overlapping regions to two speakers. It reports results on the AMI meeting corpus, the DIHARD corpus and the ETAPE corpus.
- How much weight it carries
- A preprint from the authors of a widely used open-source diarization toolkit. The abstract gives a relative improvement, not the absolute error rates of the baseline, so read it as a direction of effect rather than a benchmark score.
Facts taken from this source
- On the AMI meeting corpus, assigning overlapped speech with overlap-aware resegmentation reduced the diarization error rate of the baseline system by 20 percent relative to that baseline.
“We apply overlap-aware resegmentation on AMI, resulting in a 20% relative DER reduction over the baseline system.” (Abstract)