Probabilistic embeddings for speaker diarization

článek ve sborníku mimo WoS a Scopus

angličtina

Speaker embeddings (x-vectors) extracted from very short segments of speech have recently been shown to give competitive performance in speaker diarization. We generalize this recipe by extracting from each speech segment, in parallel with the x-vector, also a diagonal precision matrix, thus providing a path for the propagation of information about the quality of the speech segment into a PLDA scoring backend. These precisions quantify the uncertainty about what the values of the embeddings might have been if they had been extracted from high quality speech segments. The proposed probabilistic embeddings (x-vectors with precisions) are interfaced with the PLDA model by treating the x-vectors as hidden variables and marginalizing them out. We apply the proposed probabilistic embeddings as input to an agglomerative hierarchical clustering (AHC) algorithm to do diarization in the DIHARD19 evaluation set. We compute the full PLDA likelihood by the book for each clustering hypothesis that is considered by AHC. We do joint discriminative training of the PLDA parameters and of the probabilistic x-vector extractor. We demonstrate accuracy gains relative to a baseline AHC algorithm, applied to traditional xvectors (without uncertainty), and which uses averaging of binary log-likelihood-ratios, rather than by-the-book scoring.

probabilistic embeddings, speaker diarization

SILNOVA, A.; BRUMMER, J.; ROHDIN, J.; STAFYLAKIS, T.; BURGET, L.

1. 11. 2020

International Speech Communication Association

Tokyo

2312-2846

Proceedings of Odyssey: The Speaker and Language Recognition Workshop Odyssey 2014, Joensuu, Finland

2020

11

Finská republika

24

31

8

https://www.isca-speech.org/archive/Odyssey_2020/abstracts/75.html

silnova_odyssey2020_75.pdf