Generative adversarial networks in human emotion synthesis: A review
N Hajarolasvadi, MA Ramirez, W Beccaro… - IEEE …, 2020 - ieeexplore.ieee.org
Deep generative models have become an emerging topic in various research areas like
computer vision and signal processing. These models allow synthesizing realistic data …
computer vision and signal processing. These models allow synthesizing realistic data …
Deep learning serves voice cloning: how vulnerable are automatic speaker verification systems to spoofing trials?
This article verifies the reliability of automatic speaker verification (ASV) systems on new
synthesis methods based on deep neural networks. ASV systems are widely used and …
synthesis methods based on deep neural networks. ASV systems are widely used and …
Casting to corpus: Segmenting and selecting spontaneous dialogue for TTS with a CNN-LSTM speaker-dependent breath detector
This paper considers utilising breaths to create improved spontaneous-speech corpora for
conversational text-to-speech from found audio recordings such as dialogue podcasts …
conversational text-to-speech from found audio recordings such as dialogue podcasts …
[PDF][PDF] Speaker recognition-assisted robust audio deepfake detection.
Audio deepfake detection is usually formulated as a binary classification between genuine
and fake speech for an entire utterance. Environmental clues such as background and …
and fake speech for an entire utterance. Environmental clues such as background and …
Vaw-gan for singing voice conversion with non-parallel training data
Singing voice conversion aims to convert singer's voice from source to target without
changing singing content. Parallel training data is typically required for the training of …
changing singing content. Parallel training data is typically required for the training of …
Applications of deep learning to audio generation
In the recent past years, deep learning based machine learning systems have demonstrated
remarkable success for a wide range of learning tasks in multiple domains such as computer …
remarkable success for a wide range of learning tasks in multiple domains such as computer …
Noise tokens: Learning neural noise templates for environment-aware speech enhancement
H Li, J Yamagishi - arXiv preprint arXiv:2004.04001, 2020 - arxiv.org
In recent years, speech enhancement (SE) has achieved impressive progress with the
success of deep neural networks (DNNs). However, the DNN approach usually fails to …
success of deep neural networks (DNNs). However, the DNN approach usually fails to …
[PDF][PDF] High-quality Voice Conversion Using Spectrogram-Based WaveNet Vocoder.
Waveform generator is a key component in voice conversion. Recently, WaveNet waveform
generator conditioned on the Mel-cepstrum (Mcep) has shown better quality over standard …
generator conditioned on the Mel-cepstrum (Mcep) has shown better quality over standard …
[HTML][HTML] Reconstruction of Iberian ceramic potteries using generative adversarial networks
Several aspects of past culture, including historical trends, are inferred from time-based
patterns observed in archaeological artifacts belonging to different periods. The presence …
patterns observed in archaeological artifacts belonging to different periods. The presence …
[HTML][HTML] Manipulating voice attributes by adversarial learning of structured disentangled representations
Voice conversion (VC) consists of digitally altering the voice of an individual to manipulate
part of its content, primarily its identity, while maintaining the rest unchanged. Research in …
part of its content, primarily its identity, while maintaining the rest unchanged. Research in …