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 1–50 of 1249 papers

TitleStatusHype
NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech—0
Speech Quality Assessment Model Based on Mixture of Experts: System-Level Performance Enhancement and Utterance-Level Challenge Analysis—0
A Hybrid Machine Learning Framework for Optimizing Crop Selection via Agronomic and Economic Forecasting—0
DeepGesture: A conversational gesture synthesis system based on emotions and semanticsCode0
OpusLM: A Family of Open Unified Speech Language Models—0
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 LabVIEW—0
Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning ModelsCode0
ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow MatchingCode4
From Flat to Feeling: A Feasibility and Impact Study on Dynamic Facial Emotions in AI-Generated Avatars—0
S2ST-Omni: An Efficient and Scalable Multilingual Speech-to-Speech Translation Framework via Seamless Speech-Text Alignment and Streaming Speech Generation—0
UmbraTTS: Adapting Text-to-Speech to Environmental Contexts with Flow Matching—0
OmniDRCA: Parallel Speech-Text Foundation Model via Dual-Resolution Speech Representations and Contrastive AlignmentCode0
Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language ModelCode7
Seeing Voices: Generating A-Roll Video from Audio with Mirage—0
HiFiTTS-2: A Large-Scale High Bandwidth Speech Dataset—0
A Novel Data Augmentation Approach for Automatic Speaking Assessment on Opinion Expressions—0
Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions—0
CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech—0
SALF-MOS: Speaker Agnostic Latent Features Downsampled for MOS Prediction—0
Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models—0
Chain-of-Thought Training for Open E2E Spoken Dialogue Systems—0
BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models—0
ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis—0
Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modeling—0
GSA-TTS : Toward Zero-Shot Speech Synthesis based on Gradual Style Adaptor—0
DiEmo-TTS: Disentangled Emotion Representations via Self-Supervised Distillation for Cross-Speaker Emotion Transfer in Text-to-Speech—0
Revival with Voice: Multi-modal Controllable Text-to-Speech Synthesis—0
RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations—0
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingCode11
MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling—0
Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding—0
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language ModelsCode1
Pairwise Evaluation of Accent Similarity in Speech Synthesis—0
FMSD-TTS: Few-shot Multi-Speaker Multi-Dialect Text-to-Speech Synthesis for Ü-Tsang, Amdo and Kham Speech Dataset Generation—0
Articulatory Feature Prediction from Surface EMG during Speech ProductionCode0
Efficient Speech Language Modeling via Energy Distance in Continuous Latent SpaceCode2
RoVo: Robust Voice Protection Against Unauthorized Speech Synthesis with Embedding-Level Perturbations—0
OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matching—0
Shallow Flow Matching for Coarse-to-Fine Text-to-Speech Synthesis—0
UDDETTS: Unifying Discrete and Dimensional Emotions for Controllable Emotional Text-to-Speech—0
DPN-GAN: Inducing Periodic Activations in Generative Adversarial Networks for High-Fidelity Audio Synthesis—0
Investigating self-supervised features for expressive, multilingual voice conversion—0
Lightweight End-to-end Text-to-speech Synthesis for low resource on-device applications—0
LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech SynthesisCode3
Towards Flow-Matching-based TTS without Classifier-Free Guidance—0
AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation—0
Generative Adversarial Network based Voice Conversion: Techniques, Challenges, and Recent Advancements—0
FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning—0
Show:102550
← PrevPage 1 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