Výsledky vyhledávání

Report

Adaptive Isogeometric Topology Optimization of Shell Structures based on PHT-splines

Autor: Wen, Zepeng, Pan, Qiong, Zhai, Xiaoya, Kang, Hongmei, Chen, Falai

This paper proposes an Adaptive Isogeometric Topology Optimization framework for shell structures based on PHT-splines (PHT-AITO). In this framework, the design domain, displacement, and density are represented by PHT-splines. Leveraging the local re

Externí odkaz: http://arxiv.org/abs/2312.07889

Zobrazit plný text záznamu

Report

Density-based isogeometric topology optimization of shell structures

Autor: Pan, Qiong, Zhai, Xiaoya, Chen, Falai

Shell structures with a high stiffness-to-weight ratio are desirable in various engineering applications. In such scenarios, topology optimization serves as a popular and effective tool for shell structures design. Among the topology optimization met

Externí odkaz: http://arxiv.org/abs/2312.06378

Zobrazit plný text záznamu

Report

Cross-lingual Knowledge Distillation via Flow-based Voice Conversion for Robust Polyglot Text-To-Speech

Autor: Piotrowski, Dariusz, Korzeniowski, Renard, Falai, Alessio, Cygert, Sebastian, Pokora, Kamil, Tinchev, Georgi, Zhang, Ziyao, Yanagisawa, Kayoko

In this work, we introduce a framework for cross-lingual speech synthesis, which involves an upstream Voice Conversion (VC) model and a downstream Text-To-Speech (TTS) model. The proposed framework consists of 4 stages. In the first two stages, we us

Externí odkaz: http://arxiv.org/abs/2309.08255

Zobrazit plný text záznamu

Report

Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS)

Autor: Sanchez, Ariadna, Falai, Alessio, Zhang, Ziyao, Angelini, Orazio, Yanagisawa, Kayoko

An essential design decision for multilingual Neural Text-To-Speech (NTTS) systems is how to represent input linguistic features within the model. Looking at the wide variety of approaches in the literature, two main paradigms emerge, unified and sep

Externí odkaz: http://arxiv.org/abs/2207.01547

Zobrazit plný text záznamu

Report

Mix and Match: An Empirical Study on Training Corpus Composition for Polyglot Text-To-Speech (TTS)

Autor: Zhang, Ziyao, Falai, Alessio, Sanchez, Ariadna, Angelini, Orazio, Yanagisawa, Kayoko

Training multilingual Neural Text-To-Speech (NTTS) models using only monolingual corpora has emerged as a popular way for building voice cloning based Polyglot NTTS systems. In order to train these models, it is essential to understand how the compos

Externí odkaz: http://arxiv.org/abs/2207.01507

Zobrazit plný text záznamu