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 576–600 of 1249 papers

TitleStatusHype
VANI: Very-lightweight Accent-controllable TTS for Native and Non-native speakers with Identity Preservation—0
Do Prosody Transfer Models Transfer Prosody?—0
FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model—0
DTW-SiameseNet: Dynamic Time Warped Siamese Network for Mispronunciation Detection and Correction—0
ParrotTTS: Text-to-Speech synthesis by exploiting self-supervised representations—0
On the Audio-visual Synchronization for Lip-to-Speech Synthesis—0
UniFLG: Unified Facial Landmark Generator from Text or Speech—0
ClArTTS: An Open-Source Classical Arabic Text-to-Speech Corpus—0
CrossSpeech: Speaker-independent Acoustic Representation for Cross-lingual Speech Synthesis—0
Fast and small footprint Hybrid HMM-HiFiGAN based system for speech synthesis in Indian languages—0
Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Design—0
UzbekTagger: The rule-based POS tagger for Uzbek language—0
Time out of Mind: Generating Rate of Speech conditioned on emotion and speakerCode0
On granularity of prosodic representations in expressive text-to-speech—0
Multilingual Multiaccented Multispeaker TTS with RADTTS—0
Regeneration Learning: A Learning Paradigm for Data Generation—0
Applying Automated Machine Translation to Educational Video Courses—0
ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration—0
HMM-based data augmentation for E2E systems for building conversational speech synthesis systems—0
ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement—0
Investigation of Japanese PnG BERT language model in text-to-speech synthesis for pitch accent language—0
Text-to-speech synthesis based on latent variable conversion using diffusion probabilistic model and variational autoencoder—0
Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis—0
SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech—0
VideoDubber: Machine Translation with Speech-Aware Length Control for Video Dubbing—0
Show:102550
← PrevPage 24 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