SOTAVerified

Speech Synthesis

Speech synthesis is the task of generating speech from some other modality like text, lip movements etc.

Please note that the leaderboards here are not really comparable between studies - as they use mean opinion score as a metric and collect different samples from Amazon Mechnical Turk.

( Image credit: WaveNet: A generative model for raw audio )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 651–700 of 1249 papers

TitleStatusHype
Assessing Evaluation Metrics for Speech-to-Speech Translation—0
DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021Code0
CaloFlow II: Even Faster and Still Accurate Generation of Calorimeter Showers with Normalizing FlowsCode0
Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition—0
FMFCC-A: A Challenging Mandarin Dataset for Synthetic Speech DetectionCode1
From Start to Finish: Latency Reduction Strategies for Incremental Speech Synthesis in Simultaneous Speech-to-Speech Translation—0
Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attention—0
SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language ProcessingCode1
SingGAN: Generative Adversarial Network For High-Fidelity Singing Voice Generation—0
Systematic Inequalities in Language Technology Performance across the World's LanguagesCode0
DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding—0
Fine-grained style control in Transformer-based Text-to-speech SynthesisCode1
LaughNet: synthesizing laughter utterances from waveform silhouettes and a single laughter example—0
Using multiple reference audios and style embedding constraints for speech synthesis—0
Towards Lifelong Learning of Multilingual Text-To-Speech SynthesisCode0
Environment Aware Text-to-Speech Synthesis—0
Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-SpeechCode1
VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over—0
StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech SynthesisCode1
Cloning one's voice using very limited data in the wild—0
Mixer-TTS: non-autoregressive, fast and compact text-to-speech model conditioned on language model embeddingsCode1
GANtron: Emotional Speech Synthesis with Generative Adversarial Networks—0
EdiTTS: Score-based Editing for Controllable Text-to-SpeechCode1
Prosody-TTS: An end-to-end speech synthesis system with prosody control—0
On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis—0
Neural Speech Synthesis in German—0
Incorporating speaker embedding and post-filter network for improving speaker similarity of personalized speech synthesis system—0
Conditioning Sequence-to-sequence Networks with Learned Activations—0
Speech-MLP: a simple MLP architecture for speech processing—0
SynCLR: A Synthesis Framework for Contrastive Learning of out-of-domain Speech Representations—0
Guided-TTS:Text-to-Speech with Untranscribed Speech—0
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling SchemeCode1
FlowVocoder: A small Footprint Neural Vocoder based Normalizing flow for Speech Synthesis—0
Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context Prediction Network—0
"Hello, It's Me": Deep Learning-based Speech Synthesis Attacks in the Real World—0
On-device neural speech synthesis—0
fairseq S^2: A Scalable and Integrable Speech Synthesis ToolkitCode0
Referee: Towards reference-free cross-speaker style transfer with low-quality data for expressive speech synthesis—0
Physiological-Physical Feature Fusion for Automatic Voice Spoofing Detection—0
Neural Sequence-to-Sequence Speech Synthesis Using a Hidden Semi-Markov Model Based Structured Attention Mechanism—0
Neural HMMs are all you need (for high-quality attention-free TTS)Code1
Full Attention Bidirectional Deep Learning Structure for Single Channel Speech Enhancement—0
Integrated Speech and Gesture SynthesisCode0
One TTS Alignment To Rule Them AllCode1
A Unified Transformer-based Framework for Duplex Text Normalization—0
Enhancing audio quality for expressive Neural Text-to-Speech—0
A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Rate—0
Improved pronunciation prediction accuracy using morphology—0
Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis—0
Conditional Sound Generation Using Neural Discrete Time-Frequency Representation LearningCode1
Show:102550
← PrevPage 14 of 25Next →
All datasetsLibriTTSNorth American EnglishLJSpeechMandarin ChineseBlizzard Challenge 2013

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PeriodWave-Turbo-LPESQ4.45—Unverified
2BigVGAN-v2PESQ4.36—Unverified
3EVA-GAN-bigPESQ4.35—Unverified
4PeriodWave + FreeUPESQ4.25—Unverified
5RFWavePESQ4.23—Unverified
6BigVSAN (w/ snakebeta)PESQ4.12—Unverified
7BigVSANPESQ4.12—Unverified
8EVA-GAN-basePESQ4.03—Unverified
9BigVGANPESQ4.03—Unverified
10VocosPESQ3.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Tacotron 2Mean Opinion Score4.53—Unverified
2WaveNet (Linguistic)Mean Opinion Score4.34—Unverified
3WaveNet (L+F)Mean Opinion Score4.21—Unverified
4TacotronMean Opinion Score4—Unverified
5HMM-driven concatenativeMean Opinion Score3.86—Unverified
6LSTM-RNN parametricMean Opinion Score3.67—Unverified
7meansMean Opinion Score0—Unverified
#ModelMetricClaimedVerifiedStatus
1BDDM vocoderMean Opinion Score4.48—Unverified
2DiffWave LARGEMean Opinion Score4.44—Unverified
3Neural HMMMean Opinion Score3.24—Unverified
4Neural HMM Ablation with 1 state per phoneMean Opinion Score2.68—Unverified
#ModelMetricClaimedVerifiedStatus
1WaveNet (L+F)Mean Opinion Score4.08—Unverified
2LSTM-RNN parametricMean Opinion Score3.79—Unverified
3HMM-driven concatenativeMean Opinion Score3.47—Unverified
#ModelMetricClaimedVerifiedStatus
1SampleRNN (2-tier)NLL1.39—Unverified
2SampleRNN (3-tier)NLL1.39—Unverified