We design a framework for studying prelinguistic child voicefrom 3 to 24 months based on state-of-the-art algorithms in di-arization. Our system consists of a time-invariant feature ex-tractor, a context-dependent embedding generator, and a clas-sifier. We study the effect of swapping out different compo-nents of the system, as well as changing loss function, to findthe best performance. We also present a multiple-instancelearning technique that allows us to pre-train our parame-ters on larger datasets with coarser segment boundary labels.We found that our best system achieved 43.8% DER on testdataset, compared to 55.4% DER achieved by LENA soft-ware. We also found that using convolutional feature extrac-tor instead of logmel features significantly increases the per-formance of neural diarization.
@article{arxiv.2011.02698,
title = {A Comparison Study on Infant-Parent Voice Diarization},
author = {Junzhe Zhu and Mark Hasegawa-Johnson and Nancy McElwain},
journal= {arXiv preprint arXiv:2011.02698},
year = {2020}
}