7 papers
Semi-supervised Learning for Singing Synthesis Timbre
Jordi Bonada, Merlijn Blaauw
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 en…
Content Based Singing Voice Extraction From a Musical Mixture
Pritish Chandna, Merlijn Blaauw, Jordi Bonada +1
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…
Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformer
Merlijn Blaauw, Jordi Bonada
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…
A Vocoder Based Method For Singing Voice Extraction
Pritish Chandna, Merlijn Blaauw, Jordi Bonada +1
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…
WGANSing: A Multi-Voice Singing Voice Synthesizer Based on the Wasserstein-GAN
Pritish Chandna, Merlijn Blaauw, Jordi Bonada +1
We present a deep neural network based singing voice synthesizer, inspired by the Deep Convolutions Generative Adversarial Networks (DCGAN) architecture and optimized using the Was…
Data Efficient Voice Cloning for Neural Singing Synthesis
Merlijn Blaauw, Jordi Bonada, Ryunosuke Daido
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…