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 601–650 of 1249 papers

TitleStatusHype
POS-Tag Based Poetry Generation with WordNet—0
Practical Evaluation of Human and Synthesized Speech for Virtual Human Dialogue Systems—0
Predicting Expressive Speaking Style From Text In End-To-End Speech Synthesis—0
Predicting phoneme-level prosody latents using AR and flow-based Prior Networks for expressive speech synthesis—0
Predicting Phrase Breaks in Classical and Modern Standard Arabic Text—0
Predicting Romanian Stress Assignment—0
Preliminary study on using vector quantization latent spaces for TTS/VC systems with consistent performance—0
Pretraining Strategies, Waveform Model Choice, and Acoustic Configurations for Multi-Speaker End-to-End Speech Synthesis—0
PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior—0
Privacy-oriented manipulation of speaker representations—0
Probabilistic Dialogue Models with Prior Domain Knowledge—0
Probing Speaker-specific Features in Speaker Representations—0
Probing the Feasibility of Multilingual Speaker Anonymization—0
PROEMO: Prompt-Driven Text-to-Speech Synthesis Based on Emotion and Intensity Control—0
PSCodec: A Series of High-Fidelity Low-bitrate Neural Speech Codecs Leveraging Prompt Encoders—0
Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions—0
Pronunciation Dictionary-Free Multilingual Speech Synthesis by Combining Unsupervised and Supervised Phonetic Representations—0
Prosodic Clustering for Phoneme-level Prosody Control in End-to-End Speech Synthesis—0
Prosodic Prominence and Boundaries in Sequence-to-Sequence Speech Synthesis—0
Prosodic Representation Learning and Contextual Sampling for Neural Text-to-Speech—0
ProsodyFM: Unsupervised Phrasing and Intonation Control for Intelligible Speech Synthesis—0
Prosody Learning Mechanism for Speech Synthesis System Without Text Length Limit—0
Prosody-TTS: An end-to-end speech synthesis system with prosody control—0
Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis—0
Punjabi Text-To-Speech Synthesis System—0
PyDial: A Multi-domain Statistical Dialogue System Toolkit—0
pyiwn: A Python based API to access Indian Language WordNets—0
QI-TTS: Questioning Intonation Control for Emotional Speech Synthesis—0
Quantitative Analysis of Audio-Visual Tasks: An Information-Theoretic Perspective—0
RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis—0
RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations—0
Real-time Incremental Speech-to-Speech Translation of Dialogs—0
Real-Time Single-Speaker Taiwanese-Accented Mandarin Speech Synthesis System—0
ReCAB-VAE: Gumbel-Softmax Variational Inference Based on Analytic Divergence—0
Recurrent Neural Network Postfilters for Statistical Parametric Speech Synthesis—0
RedPen: Region- and Reason-Annotated Dataset of Unnatural Speech—0
Referee: Towards reference-free cross-speaker style transfer with low-quality data for expressive speech synthesis—0
Refer-iTTS: A System for Referring in Spoken Installments to Objects in Real-World Images—0
Regeneration Learning: A Learning Paradigm for Data Generation—0
Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability—0
DLPO: Diffusion Model Loss-Guided Reinforcement Learning for Fine-Tuning Text-to-Speech Diffusion Models—0
Removing Speaker Information from Speech Representation using Variable-Length Soft Pooling—0
Replay Spoofing Countermeasure Using Autoencoder and Siamese Network on ASVspoof 2019 Challenge—0
Residual-guided Personalized Speech Synthesis based on Face Image—0
Response Generation Based on Hierarchical Semantic Structure with POMDP Re-ranking for Conversational Dialogue Systems—0
Retrieval-Augmented Audio Deepfake Detection—0
Review of end-to-end speech synthesis technology based on deep learning—0
ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement—0
ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration—0
Revival with Voice: Multi-modal Controllable Text-to-Speech Synthesis—0
Show:102550
← PrevPage 13 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