An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis

Lorincz, Beata; Stan, Adriana; Giurgiu, Mircea

doi:10.1016/j.procs.2021.08.078

Cited by 1 publication

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…t-SNE is a popular dimensionality reduction and visualization technique that was introduced in 2008 by van der Matten and Hinton [36]. It has been applied towards a variety of high-dimensional data, including deep learning [21], physics [37], and medicine [1]. Given a high-dimensional dataset, t-SNE outputs a low-dimensional representation.…”

Section: Introductionmentioning

confidence: 99%

AVIDA: Alternating method for Visualizing and Integrating Data

Dover¹,

Cang²,

Ma³

et al. 2022

Preprint

View full text Add to dashboard Cite

High-dimensional multimodal data arises in many scientific fields. The integration of multimodal data becomes challenging when there is no known correspondence between the samples and the features of different datasets. To tackle this challenge, we introduce AVIDA, a framework for simultaneously performing data alignment and dimension reduction. In the numerical experiments, Gromov-Wasserstein optimal transport and t-distributed stochastic neighbor embedding are used as the alignment and dimension reduction modules respectively. We show that AVIDA correctly aligns high-dimensional datasets without common features with four synthesized datasets and two real multimodal single-cell datasets. Compared to several existing methods, we demonstrate that AVIDA better preserves structures of individual datasets, especially distinct local structures in the joint lowdimensional visualization, while achieving comparable alignment performance. Such a property is important in multimodal single-cell data analysis as some biological processes are uniquely captured by one of the datasets. In general applications, other methods can be used for the alignment and dimension reduction modules.

show abstract

Section: Introductionmentioning

confidence: 99%