Picture for Axel Roebel

Axel Roebel

Lina-Speech: Gated Linear Attention is a Fast and Parameter-Efficient Learner for text-to-speech synthesis

Add code
Oct 30, 2024
Figure 1 for Lina-Speech: Gated Linear Attention is a Fast and Parameter-Efficient Learner for text-to-speech synthesis
Figure 2 for Lina-Speech: Gated Linear Attention is a Fast and Parameter-Efficient Learner for text-to-speech synthesis
Figure 3 for Lina-Speech: Gated Linear Attention is a Fast and Parameter-Efficient Learner for text-to-speech synthesis
Figure 4 for Lina-Speech: Gated Linear Attention is a Fast and Parameter-Efficient Learner for text-to-speech synthesis
Viaarxiv icon

Audio Conditioning for Music Generation via Discrete Bottleneck Features

Add code
Jul 17, 2024
Viaarxiv icon

Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis

Add code
Jun 06, 2024
Viaarxiv icon

VaSAB: The variable size adaptive information bottleneck for disentanglement on speech and singing voice

Add code
Oct 05, 2023
Viaarxiv icon

Analysis and transformations of intensity in singing voice

Add code
Apr 08, 2022
Figure 1 for Analysis and transformations of intensity in singing voice
Figure 2 for Analysis and transformations of intensity in singing voice
Figure 3 for Analysis and transformations of intensity in singing voice
Figure 4 for Analysis and transformations of intensity in singing voice
Viaarxiv icon

StyleWaveGAN: Style-based synthesis of drum sounds with extensive controls using generative adversarial networks

Add code
Apr 02, 2022
Figure 1 for StyleWaveGAN: Style-based synthesis of drum sounds with extensive controls using generative adversarial networks
Figure 2 for StyleWaveGAN: Style-based synthesis of drum sounds with extensive controls using generative adversarial networks
Figure 3 for StyleWaveGAN: Style-based synthesis of drum sounds with extensive controls using generative adversarial networks
Figure 4 for StyleWaveGAN: Style-based synthesis of drum sounds with extensive controls using generative adversarial networks
Viaarxiv icon

Audio Defect Detection in Music with Deep Networks

Add code
Feb 11, 2022
Figure 1 for Audio Defect Detection in Music with Deep Networks
Figure 2 for Audio Defect Detection in Music with Deep Networks
Figure 3 for Audio Defect Detection in Music with Deep Networks
Figure 4 for Audio Defect Detection in Music with Deep Networks
Viaarxiv icon

Sequence-To-Sequence Voice Conversion using F0 and Time Conditioning and Adversarial Learning

Add code
Oct 07, 2021
Figure 1 for Sequence-To-Sequence Voice Conversion using F0 and Time Conditioning and Adversarial Learning
Figure 2 for Sequence-To-Sequence Voice Conversion using F0 and Time Conditioning and Adversarial Learning
Viaarxiv icon

Towards Universal Neural Vocoding with a Multi-band Excited WaveNet

Add code
Oct 07, 2021
Figure 1 for Towards Universal Neural Vocoding with a Multi-band Excited WaveNet
Figure 2 for Towards Universal Neural Vocoding with a Multi-band Excited WaveNet
Viaarxiv icon

Beyond Voice Identity Conversion: Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations

Add code
Jul 27, 2021
Figure 1 for Beyond Voice Identity Conversion: Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations
Figure 2 for Beyond Voice Identity Conversion: Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations
Figure 3 for Beyond Voice Identity Conversion: Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations
Figure 4 for Beyond Voice Identity Conversion: Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations
Viaarxiv icon