Analysis of Speaker Diarization based on Bayesian HMM with Eigenvoice Priors

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F19%3APU134972" target="_blank" >RIV/00216305:26230/19:PU134972 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/00216305:26230/20:PU134972

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/8910412" target="_blank" >https://ieeexplore.ieee.org/document/8910412</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TASLP.2019.2955293" target="_blank" >10.1109/TASLP.2019.2955293</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Analysis of Speaker Diarization based on Bayesian HMM with Eigenvoice Priors

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Analysis of Speaker Diarization based on Bayesian HMM with Eigenvoice Priors

Popis výsledku anglicky

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.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING

ISSN

2329-9290

e-ISSN

2329-9304

Svazek periodika

28

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

14

Strana od-do

355-368

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85075649332