Speaker Diarization based on Bayesian HMM with Eigenvoice Priors

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU130759" target="_blank" >RIV/00216305:26230/18:PU130759 - isvavai.cz</a>
Result on the web
<a href="https://www.fit.vut.cz/research/publication/11786/" target="_blank" >https://www.fit.vut.cz/research/publication/11786/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.21437/Odyssey.2018-21" target="_blank" >10.21437/Odyssey.2018-21</a>

Result language
angličtina
Original language name
Speaker Diarization based on Bayesian HMM with Eigenvoice Priors
Original language description
Nowadays, most speaker diarization methods address the task in two steps: segmentation of the input conversation into (preferably) speaker homogeneous segments, and clustering. Generally, different models and techniques are used for the two steps. In this paper we present a very elegant approach where a straightforward and efficient Variational Bayes (VB) inference in a single probabilistic model addresses the complete SD problem. Our model is a Bayesian Hidden Markov Model, in which states represent speaker specific distributions and transitions between states represent speaker turns. As in the ivector or JFA models, speaker distributions are modeled by GMMs with parameters constrained by eigenvoice priors. This allows to robustly estimate the speaker models from very short speech segments. The model, which was released as open source code and has already been used by several labs, is fully described for the first time in this paper. We present results and the system is compared and combined with other state-of-the-art approaches. The model provides the best results reported so far on the CALLHOME dataset.
Czech name
—
Czech description
—

Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project
<a href="/en/project/LQ1602" target="_blank" >LQ1602: IT4Innovations excellence in science</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)