Zobrazeno 1 - 10
of 129
pro vyhledávání: '"Bonada, Jordi"'
Publikováno v:
In Thin-Walled Structures September 2024 202
Publikováno v:
In Thin-Walled Structures February 2024 195
Autor:
Bonada, Jordi, Blaauw, Merlijn
We propose a semi-supervised singing synthesizer, which is able to learn new voices from audio data only, without any annotations such as phonetic segmentation. Our system is an encoder-decoder model with two encoders, linguistic and acoustic, and on
Externí odkaz:
http://arxiv.org/abs/2011.02809
Choral singing is a widely practiced form of ensemble singing wherein a group of people sing simultaneously in polyphonic harmony. The most commonly practiced setting for choir ensembles consists of four parts; Soprano, Alto, Tenor and Bass (SATB), e
Externí odkaz:
http://arxiv.org/abs/2008.07645
Publikováno v:
2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain
We present a deep learning based methodology for extracting the singing voice signal from a musical mixture based on the underlying linguistic content. Our model follows an encoder decoder architecture and takes as input the magnitude component of th
Externí odkaz:
http://arxiv.org/abs/2002.04933
Autor:
Blaauw, Merlijn, Bonada, Jordi
We propose a sequence-to-sequence singing synthesizer, which avoids the need for training data with pre-aligned phonetic and acoustic features. Rather than the more common approach of a content-based attention mechanism combined with an autoregressiv
Externí odkaz:
http://arxiv.org/abs/1910.09989
Investigation on the down-aisle ductility of multiple bay pallet racks by means of pushover analyses
Publikováno v:
In Engineering Structures 1 July 2023 286
Publikováno v:
2019 27th European Signal Processing Conference (EUSIPCO)
We present a deep neural network based singing voice synthesizer, inspired by the Deep Convolutions Generative Adversarial Networks (DCGAN) architecture and optimized using the Wasserstein-GAN algorithm. We use vocoder parameters for acoustic modelli
Externí odkaz:
http://arxiv.org/abs/1903.10729
Publikováno v:
ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
This paper presents a novel method for extracting the vocal track from a musical mixture. The musical mixture consists of a singing voice and a backing track which may comprise of various instruments. We use a convolutional network with skip and resi
Externí odkaz:
http://arxiv.org/abs/1903.07554
There are many use cases in singing synthesis where creating voices from small amounts of data is desirable. In text-to-speech there have been several promising results that apply voice cloning techniques to modern deep learning based models. In this
Externí odkaz:
http://arxiv.org/abs/1902.07292