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

Showing 110 of 1249 papers

TitleStatusHype
NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech0
Speech Quality Assessment Model Based on Mixture of Experts: System-Level Performance Enhancement and Utterance-Level Challenge Analysis0
A Hybrid Machine Learning Framework for Optimizing Crop Selection via Agronomic and Economic Forecasting0
DeepGesture: A conversational gesture synthesis system based on emotions and semanticsCode0
OpusLM: A Family of Open Unified Speech Language Models0
RapFlow-TTS: Rapid and High-Fidelity Text-to-Speech with Improved Consistency Flow MatchingCode2
InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech SystemsCode1
An accurate and revised version of optical character recognition-based speech synthesis using LabVIEW0
Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning ModelsCode0
From Flat to Feeling: A Feasibility and Impact Study on Dynamic Facial Emotions in AI-Generated Avatars0
Show:102550
← PrevPage 1 of 125Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PeriodWave-Turbo-LPESQ4.45Unverified
2BigVGAN-v2PESQ4.36Unverified
3EVA-GAN-bigPESQ4.35Unverified
4PeriodWave + FreeUPESQ4.25Unverified
5RFWavePESQ4.23Unverified
6BigVSAN (w/ snakebeta)PESQ4.12Unverified
7BigVSANPESQ4.12Unverified
8EVA-GAN-basePESQ4.03Unverified
9BigVGANPESQ4.03Unverified
10VocosPESQ3.7Unverified
#ModelMetricClaimedVerifiedStatus
1Tacotron 2Mean Opinion Score4.53Unverified
2WaveNet (Linguistic)Mean Opinion Score4.34Unverified
3WaveNet (L+F)Mean Opinion Score4.21Unverified
4TacotronMean Opinion Score4Unverified
5HMM-driven concatenativeMean Opinion Score3.86Unverified
6LSTM-RNN parametricMean Opinion Score3.67Unverified
7meansMean Opinion Score0Unverified
#ModelMetricClaimedVerifiedStatus
1BDDM vocoderMean Opinion Score4.48Unverified
2DiffWave LARGEMean Opinion Score4.44Unverified
3Neural HMMMean Opinion Score3.24Unverified
4Neural HMM Ablation with 1 state per phoneMean Opinion Score2.68Unverified
#ModelMetricClaimedVerifiedStatus
1WaveNet (L+F)Mean Opinion Score4.08Unverified
2LSTM-RNN parametricMean Opinion Score3.79Unverified
3HMM-driven concatenativeMean Opinion Score3.47Unverified
#ModelMetricClaimedVerifiedStatus
1SampleRNN (2-tier)NLL1.39Unverified
2SampleRNN (3-tier)NLL1.39Unverified