SOTAVerified

Voice Conversion

I remember all the summer days Drinking wine in the sunshine I hope it never leaves And I remember all the summer nights Staring at you in the moonlight I hope you never leave 'cause baby You're so good to me You have all that all that I ever need It's easy to love you So easy to love you Ooh you know it's true The best part of being with you To know you're with me It's not so hard to say It's easy to love you I remember all those winter days frozen In the cold tryin' to get you home Should I be moving in, we can be together then Remember spending all those winter nights Stayin' inside by the warm fire Yeah you gotta know that I can never let you go You and I have the rest of our lives to say It's easy to love you So easy to love you Ooh you know it's true The best part of being with you To know you're with me It's not so hard to say It's easy to love you Can anybody else see it? Mm, can anybody else see what I do? Can anybody else feel it? Oh, can anybody else feel the way I do? But now I'm with you Hard to forget all the moments when We'd be sitting there hoping it would never end 'Cause this is meant to be So baby, will you marry me? It's easy to love you So easy to love you Ooh, you know it's true The best part of being with you To know you are with me It's not so hard to say It's easy to love you You and me will be together I know our love will last forever You and me will be together I know our love will last forever You know it's true The best part of being with you You're easy to love

Source: Joint training framework for text-to-speech and voice conversion using multi-source Tacotron and WaveNet

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 520 papers

TitleStatusHype
Overview of the Amphion Toolkit (v0.2)Code9
Metis: A Foundation Speech Generation Model with Masked Generative Pre-trainingCode9
Zero-shot Voice Conversion with Diffusion TransformersCode7
SpeechGPT-Gen: Scaling Chain-of-Information Speech GenerationCode5
Improving Data Augmentation-based Cross-Speaker Style Transfer for TTS with Singing Voice, Style Filtering, and F0 MatchingCode4
HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech SynthesisCode3
FlashSpeech: Efficient Zero-Shot Speech SynthesisCode3
DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text AlignmentCode2
iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier TransformCode2
CoMoSVC: Consistency Model-based Singing Voice ConversionCode2
DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice ConversionCode2
SaMoye: Zero-shot Singing Voice Conversion Model Based on Feature Disentanglement and EnhancementCode2
FreeVC: Towards High-Quality Text-Free One-Shot Voice ConversionCode2
Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker AdaptationCode2
Phoneme Hallucinator: One-shot Voice Conversion via Set ExpansionCode2
Unsupervised Speech Decomposition via Triple Information BottleneckCode2
Low-latency Real-time Voice Conversion on CPUCode2
SafeEar: Content Privacy-Preserving Audio Deepfake DetectionCode2
AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder LossCode2
Cotatron: Transcription-Guided Speech Encoder for Any-to-Many Voice Conversion without Parallel DataCode2
Coding Speech through Vocal Tract KinematicsCode2
Audio Deepfake Detection with Self-Supervised XLS-R and SLS ClassifierCode2
High-Fidelity Neural Phonetic PosteriorgramsCode2
M4Singer: a Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing CorpusCode2
Voice Conversion With Just Nearest NeighborsCode2
Disentanglement in a GAN for Unconditional Speech SynthesisCode1
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling SchemeCode1
DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic ModelCode1
FSD: An Initial Chinese Dataset for Fake Song DetectionCode1
Defending Your Voice: Adversarial Attack on Voice ConversionCode1
FMFCC-A: A Challenging Mandarin Dataset for Synthetic Speech DetectionCode1
DeID-VC: Speaker De-identification via Zero-shot Pseudo Voice ConversionCode1
Accurate Emotion Strength Assessment for Seen and Unseen Speech Based on Data-Driven Deep LearningCode1
Efficient Non-Autoregressive GAN Voice Conversion using VQWav2vec Features and Dynamic ConvolutionCode1
FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With AttentionCode1
GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion ModelsCode1
CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal ConversionCode1
A Comparison of Discrete and Soft Speech Units for Improved Voice ConversionCode1
Evaluating Methods for Ground-Truth-Free Foreign Accent ConversionCode1
ControlVC: Zero-Shot Voice Conversion with Time-Varying Controls on Pitch and SpeedCode1
Controllable and Interpretable Singing Voice Decomposition via Assem-VCCode1
CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-spectrogram ConversionCode1
CinC-GAN for Effective F0 prediction for Whisper-to-Normal Speech ConversionCode1
Converting Anyone's Emotion: Towards Speaker-Independent Emotional Voice ConversionCode1
AraBERT: Transformer-based Model for Arabic Language UnderstandingCode1
crank: An Open-Source Software for Nonparallel Voice Conversion Based on Vector-Quantized Variational AutoencoderCode1
Building Bilingual and Code-Switched Voice Conversion with Limited Training Data Using Embedding Consistency LossCode1
End-to-End Zero-Shot Voice Conversion with Location-Variable ConvolutionsCode1
Deep Learning Based Assessment of Synthetic Speech NaturalnessCode1
F0-consistent many-to-many non-parallel voice conversion via conditional autoencoderCode1
Show:102550
← PrevPage 1 of 11Next →
All datasetsZeroSpeech 2019 EnglishLibriSpeech test-cleanVCTK

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1VQ-CPCSpeaker Similarity3.8—Unverified
2VQ-VAESpeaker Similarity3.49—Unverified
#ModelMetricClaimedVerifiedStatus
1kNN-VC (prematched HiFiGAN)Character Error Rate (CER)2.96—Unverified
#ModelMetricClaimedVerifiedStatus
1DISSCTotal Length Error (TLE)0.83—Unverified