Disentangled speech representation learning based on factorized hierarchical variational autoencoder with self-supervised objective

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

1 Citationer (Scopus)

Abstrakt

Disentangled representation learning aims to extract explanatory features or factors and retain salient information. Factorized hierarchical variational autoencoder (FHVAE) presents a way to disentangle a speech signal into sequential-level and segmental-level features, which represent speaker identity and speech content information, respectively. As a self-supervised objective, autoregressive predictive coding (APC), on the other hand, has been used in extracting meaningful and transferable speech features for multiple downstream tasks. Inspired by the success of these two representation learning methods, this paper proposes to integrate the APC objective into the FHVAE framework aiming at benefiting from the additional self-supervision target. The main proposed method requires neither more training data nor more computational cost at test time, but obtains improved meaningful representations while maintaining disentanglement. The experiments were conducted on the TIMIT dataset. Results demonstrate that FHVAE equipped with the additional self-supervised objective is able to learn features providing superior performance for tasks including speech recognition and speaker recognition. Furthermore, voice conversion, as one application of disentangled representation learning, has been applied and evaluated. The results show performance similar to baseline of the new framework on voice conversion.

OriginalsprogEngelsk
Titel2021 IEEE 31st International Workshop on Machine Learning for Signal Processing, MLSP 2021
Antal sider6
ForlagIEEE
Publikationsdato28 okt. 2021
Sider1-6
Artikelnummer9596320
ISBN (Trykt)978-1-6654-1184-4
ISBN (Elektronisk)978-1-7281-6338-3
DOI
StatusUdgivet - 28 okt. 2021
Begivenhed2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) - Gold Coast, Australien
Varighed: 25 okt. 202128 okt. 2021

Konference

Konference2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)
Land/OmrådeAustralien
ByGold Coast
Periode25/10/202128/10/2021
NavnIEEE Workshop on Machine Learning for Signal Processing
ISSN1551-2541

Fingeraftryk

Dyk ned i forskningsemnerne om 'Disentangled speech representation learning based on factorized hierarchical variational autoencoder with self-supervised objective'. Sammen danner de et unikt fingeraftryk.

Citationsformater