Extracting speaker and emotion information from self-supervised speech models via channel-wise correlations

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F23%3APU149387" target="_blank" >RIV/00216305:26230/23:PU149387 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10023345" target="_blank" >https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10023345</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/SLT54892.2023.10023345" target="_blank" >10.1109/SLT54892.2023.10023345</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Extracting speaker and emotion information from self-supervised speech models via channel-wise correlations

Popis výsledku v původním jazyce

Self-supervised learning of speech representations from large amounts of unlabeled data has enabled state-of-the-art results in several speech processing tasks. Aggregating these speech representations across time is typically approached by using descriptive statistics, and in particular, using the first- and second-order statistics of representation coefficients. In this paper, we examine an alternative way of extracting speaker and emotion information from self-supervised trained models, based on the correlations between the coefficients of the representations - correlation pooling. We show improvements over mean pooling and further gains when the pooling methods are combined via fusion. The code is available at github.com/Lamomal/s3prl_correlation.

Název v anglickém jazyce

Extracting speaker and emotion information from self-supervised speech models via channel-wise correlations

Popis výsledku anglicky

Self-supervised learning of speech representations from large amounts of unlabeled data has enabled state-of-the-art results in several speech processing tasks. Aggregating these speech representations across time is typically approached by using descriptive statistics, and in particular, using the first- and second-order statistics of representation coefficients. In this paper, we examine an alternative way of extracting speaker and emotion information from self-supervised trained models, based on the correlations between the coefficients of the representations - correlation pooling. We show improvements over mean pooling and further gains when the pooling methods are combined via fusion. The code is available at github.com/Lamomal/s3prl_correlation.

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

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

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings

ISBN

978-1-6654-7189-3

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

1136-1143

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Doha

Místo konání akce

Doha

Datum konání akce

9. 1. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000968851900153