Publication Details
Analysis of Speaker Diarization based on Bayesian HMM with Eigenvoice Priors
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Landini Federico Nicolás, Ph.D. (RG SPEECH)
Černocký Jan, prof. Dr. Ing. (DCGM)
Hidden Markov Models, Bayes methods, Task analysis, Probabilistic logic,
Training, Speech processing, Complexity theory
In our previous work, we introduced our Bayesian Hidden Markov Model with
eigenvoice priors, which has been recently recognized as the state-of-the-art
model for Speaker Diarization. In this paper we present a more complete analysis
of the Diarization system. The inference of the model is fully described and
derivations of all update formulas are provided for a complete understanding of
the algorithm. An extensive analysis on the effect, sensitivity and interactions
of all model parameters is provided, which might be used as a guide for their
optimal setting. The newly introduced speaker regularization coefficient allows
us to control the number of speakers inferred in an utterance. A naive speaker
model merging strategy is also presented, which allows to drive the variational
inference out of local optima. Experiments for the different diarization
scenarios are presented on CALLHOME and DIHARD datasets.
@article{BUT161472,
author="Mireia {Diez Sánchez} and Lukáš {Burget} and Federico Nicolás {Landini} and Jan {Černocký}",
title="Analysis of Speaker Diarization based on Bayesian HMM with Eigenvoice Priors",
journal="IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING",
year="2020",
volume="28",
number="1",
pages="355--368",
doi="10.1109/TASLP.2019.2955293",
issn="2329-9290",
url="https://ieeexplore.ieee.org/document/8910412"
}