Optimizing Bayesian Hmm Based X-Vector Clustering for the Second Dihard Speech Diarization Challenge

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F20%3APU136482" target="_blank" >RIV/00216305:26230/20:PU136482 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9053982" target="_blank" >https://ieeexplore.ieee.org/document/9053982</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP40776.2020.9053982" target="_blank" >10.1109/ICASSP40776.2020.9053982</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Optimizing Bayesian Hmm Based X-Vector Clustering for the Second Dihard Speech Diarization Challenge

Popis výsledku v původním jazyce

This paper presents an analysis of our diarization system winning the second DIHARD speech diarization challenge, track 1. This system is based on clustering x-vector speaker embeddings extracted every 0.25s from short segments of the input recording. In this paper, we focus on the two x-vector clustering methods employed, namely Agglomerative Hierarchical Clustering followed by a clustering based on Bayesian Hidden Markov Model (BHMM). Even though the system submitted to the challenge had further post-processing steps, we will show that using this BHMM solely is enough to achieve the best performance in the challenge. The analysis will show improvements achieved by optimizing individual processing steps, including a simple procedure to effectively perform "domain adaptation" by Probabilistic Linear Discriminant Analysis model interpolation. All experiments are performed in the DIHARD II evaluation framework.

Název v anglickém jazyce

Optimizing Bayesian Hmm Based X-Vector Clustering for the Second Dihard Speech Diarization Challenge

Popis výsledku anglicky

This paper presents an analysis of our diarization system winning the second DIHARD speech diarization challenge, track 1. This system is based on clustering x-vector speaker embeddings extracted every 0.25s from short segments of the input recording. In this paper, we focus on the two x-vector clustering methods employed, namely Agglomerative Hierarchical Clustering followed by a clustering based on Bayesian Hidden Markov Model (BHMM). Even though the system submitted to the challenge had further post-processing steps, we will show that using this BHMM solely is enough to achieve the best performance in the challenge. The analysis will show improvements achieved by optimizing individual processing steps, including a simple procedure to effectively perform "domain adaptation" by Probabilistic Linear Discriminant Analysis model interpolation. All experiments are performed in the DIHARD II evaluation framework.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/LQ1602" target="_blank" >LQ1602: IT4Innovations excellence in science</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ISBN

978-1-5090-6631-5

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

6519-6523

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Barcelona

Místo konání akce

Barcelona

Datum konání akce

4. 5. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000615970406156