Sequence-to-Sequence Voice Conversion with Similarity Metric Learned Using Generative Adversarial Networks
Explore this paper's citation graph
Summary
The proposed SVC framework uses a similarity metric implicitly derived from a generative adversarial network, enabling the measurement of the distance in the high-level abstract space to mitigate the oversmoothing problem caused in the low-level data space.
- Type
- article
- Published
- 2017-08-20
- Cited by
- 111
- References
- 37
- OpenAlex
- https://openalex.org/W2747744257
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:11472563
Keywords
Sequence (biology), Generative grammar, Similarity (geometry), Computer science, Adversarial system
References
- Statistical methods for voice quality transformation
- Low-delay voice conversion based on maximum likelihood estimation of spectral parameter trajectory
- Voice conversion using deep Bidirectional Long Short-Term Memory based Recurrent Neural Networks
- Maximum likelihood voice conversion based on GMM with STRAIGHT mixed excitation
- Rectified Linear Units Improve Restricted Boltzmann Machines
- Convolutional Neural Networks for Sentence Classification
- Fully convolutional networks for semantic segmentation
- Empirical Evaluation of Rectified Activations in Convolutional Network
- Exemplar-Based Voice Conversion Using Sparse Representation in Noisy Environments
- Exemplar-Based Sparse Representation With Residual Compensation for Voice Conversion
- A postfilter to modify the modulation spectrum in HMM-based speech synthesis
- A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis
- Voice conversion using deep neural networks with speaker-independent pre-training
- Voice Conversion Using Deep Neural Networks With Layer-Wise Generative Training
- A system for voice conversion based on probabilistic classification and a harmonic plus noise model
- High Quality Voice Conversion through Phoneme-Based Linear Mapping Functions with STRAIGHT for Mandarin
- Voice Conversion Based on Speaker-Dependent Restricted Boltzmann Machines
- INCA Algorithm for Training Voice Conversion Systems From Nonparallel Corpora
- Character-level Convolutional Networks for Text Classification
- Statistical singing voice conversion with direct waveform modification based on the spectrum differential
Cited by
- Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks
- Conditional End-to-End Audio Transforms
- A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation
- Speech Waveform Synthesis from MFCC Sequences with Generative Adversarial Networks
- Time-Frequency Masking-Based Speech Enhancement Using Generative Adversarial Network
- Generative adversarial networks: Foundations and applications
- Semi-blind source separation with multichannel variational autoencoder
- ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder
- Effectiveness of Generative Adversarial Network for Non-Audible Murmur-to-Whisper Speech Conversion
- Vae-Space: Deep Generative Model of Voice Fundamental Frequency Contours
- Sequence-to-Sequence Acoustic Modeling for Voice Conversion
- ConvS2S-VC: Fully convolutional sequence-to-sequence voice conversion
- Nonparallel Emotional Speech Conversion
- ATTS2S-VC: Sequence-to-sequence Voice Conversion with Attention and Context Preservation Mechanisms
- Adaptive Wavenet Vocoder for Residual Compensation in GAN-Based Voice Conversion
- Synthetic-to-Natural Speech Waveform Conversion Using Cycle-Consistent Adversarial Networks
- Generative Adversarial Networksの基礎と応用
- Neutral-to-emotional voice conversion with cross-wavelet transform F0 using generative adversarial networks
- Time-Frequency Mask-based Speech Enhancement using Convolutional Generative Adversarial Network
- Novel Inter Mixture Weighted GMM Posteriorgram for DNN and GAN-based Voice Conversion
Related papers
- Image Super-Resolution with Text Handling Via Generative Adversairal Network
- Aynı Şartlar Altında Farklı Üretici Çekişmeli Ağların Karşılaştırılması
- The Study and Implementation on Adversarial Attack Algorithm Based on Deep Convolutional Generative Adversarial Network
- 形状設計タスクにおける深層生成モデルとPhysics Guided GAN
- The Role of Generative Adversarial Networks in Radiation Reduction and Artifact Correction in Medical Imaging.
- Image Generation Using Different Models Of Generative Adversarial Network
- Realistic Hair Synthesis with Generative Adversarial Networks
- Physics guided deep learning generative models for crystal materials discovery