Detail publikace

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

STAFYLAKIS, T. MOŠNER, L. KAKOUROS, S. PLCHOT, O. BURGET, L. ČERNOCKÝ, J.

Originální název

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

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

Speaker identification, speaker verification, emotion recognition, self-supervised models

Autoři

STAFYLAKIS, T.; MOŠNER, L.; KAKOUROS, S.; PLCHOT, O.; BURGET, L.; ČERNOCKÝ, J.

Vydáno

9. 1. 2023

Nakladatel

IEEE Signal Processing Society

Místo

Doha

ISBN

978-1-6654-7189-3

Kniha

2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings

Strany od

1136

Strany do

1143

Strany počet

8

URL

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10023345

BibTex

@inproceedings{BUT185160,
  author="STAFYLAKIS, T. and MOŠNER, L. and KAKOUROS, S. and PLCHOT, O. and BURGET, L. and ČERNOCKÝ, J.",
  title="Extracting speaker and emotion information from self-supervised speech models via channel-wise correlations",
  booktitle="2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings",
  year="2023",
  pages="1136--1143",
  publisher="IEEE Signal Processing Society",
  address="Doha",
  doi="10.1109/SLT54892.2023.10023345",
  isbn="978-1-6654-7189-3",
  url="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10023345"
}

Dokumenty

stafylakis_SLT2022_published in year 2023.pdf