Disentangled speech representation learning based on factorized hierarchical variational autoencoder with self-supervised objective
Y Xie, T Arildsen, ZH Tan - 2021 IEEE 31st International …, 2021 - ieeexplore.ieee.org
Disentangled representation learning aims to extract explanatory features or factors and
retain salient information. Factorized hierarchical variational autoencoder (FHVAE) presents …
retain salient information. Factorized hierarchical variational autoencoder (FHVAE) presents …
Integration of variational autoencoder and spatial clustering for adaptive multi-channel neural speech separation
In this paper, we propose a method combining variational autoencoder model of speech
with a spatial clustering approach for multi-channel speech separation. The advantage of …
with a spatial clustering approach for multi-channel speech separation. The advantage of …
Adversarial one-shot voice conversion using disentangled representations
A Yeşilkanat - 2020 - 193.140.201.98
In this thesis, a new adversarial one-shot voice conversion (VC) method is introduced by
enhancing one of the latest variational autoencoder based one-shot VC methods. The …
enhancing one of the latest variational autoencoder based one-shot VC methods. The …
[PDF][PDF] Disentangling the Dimensions of Phonetic Variation: First Steps towards and Explanatory and Exploratory Research Tool in Phonetics
P Wagner, R Haeb-Umbach - 2019 - core.ac.uk
In this paper, we present first evidence for a potential application of novel speech
technological methods as a valuable tool for basic phonetics research. We describe a …
technological methods as a valuable tool for basic phonetics research. We describe a …