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 851–875 of 1249 papers

TitleStatusHype
A Transfer Learning End-to-End ArabicText-To-Speech (TTS) Deep Architecture—0
Prosodic Prominence and Boundaries in Sequence-to-Sequence Speech Synthesis—0
Recurrent Quantum Neural NetworksCode0
Normalizing Text using Language Modelling based on Phonetics and String Similarity—0
Articulatory-WaveNet: Autoregressive Model For Acoustic-to-Articulatory Inversion—0
SE-MelGAN -- Speaker Agnostic Rapid Speech Enhancement—0
NanoFlow: Scalable Normalizing Flows with Sublinear Parameter ComplexityCode1
FastSpeech 2: Fast and High-Quality End-to-End Text to SpeechCode1
WaveNODE: A Continuous Normalizing Flow for Speech SynthesisCode1
Analysis and Synthesis of Hypo and Hyperarticulated Speech—0
End-to-End Adversarial Text-to-SpeechCode1
PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitivesCode1
\'Etude comparative des param\`etres d'entr\'ee pour la synth\`ese expressive audiovisuelle de la parole par DNNs (Comparative study of input parameters for DNN-based expressive audiovisual speech synthesis )—0
A comparison of Vietnamese Statistical Parametric Speech Synthesis Systems—0
Noise Robust TTS for Low Resource Speakers using Pre-trained Model and Speech Enhancement—0
Transformer VQ-VAE for Unsupervised Unit Discovery and Speech Synthesis: ZeroSpeech 2020 Challenge—0
NAUTILUS: a Versatile Voice Cloning System—0
Cross-lingual Multispeaker Text-to-Speech under Limited-Data Scenario—0
Evaluating Features and Metrics for High-Quality Simulation of Early Vocal Learning of Vowels—0
Investigation of learning abilities on linguistic features in sequence-to-sequence text-to-speech synthesis—0
Bayesian Subspace HMM for the Zerospeech 2020 Challenge—0
Learning Individual Speaking Styles for Accurate Lip to Speech SynthesisCode1
Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation—0
You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation—0
Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech SynthesisCode1
Show:102550
← PrevPage 35 of 50Next →
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