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 151–200 of 1249 papers

TitleStatusHype
Audio Codec Augmentation for Robust Collaborative Watermarking of Speech SynthesisCode0
NDVQ: Robust Neural Audio Codec with Normal Distribution-Based Vector Quantization—0
Enhancing Multilingual Speech Generation and Recognition Abilities in LLMs with Constructed Code-switched Data—0
Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation—0
StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion—0
Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization—0
Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation—0
LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study—0
Text-To-Speech Synthesis In The Wild—0
Full-text Error Correction for Chinese Speech Recognition with Large Language Model—0
SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and SynthesisCode2
Enhancing Kurdish Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approach—0
What happens to diffusion model likelihood when your model is conditional?—0
AS-Speech: Adaptive Style For Speech Synthesis—0
Fast, High-Quality and Parameter-Efficient Articulatory Synthesis using Differentiable DSP—0
VoxHakka: A Dialectally Diverse Multi-speaker Text-to-Speech System for Taiwanese Hakka—0
vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoders—0
Sample-Efficient Diffusion for Text-To-Speech SynthesisCode2
SelectTTS: Synthesizing Anyone's Voice via Discrete Unit-Based Frame Selection—0
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language ModelCode3
Mini-Omni: Language Models Can Hear, Talk While Thinking in StreamingCode7
Literary and Colloquial Dialect Identification for Tamil using Acoustic Features—0
SpeechCraft: A Fine-grained Expressive Speech Dataset with Natural Language DescriptionCode2
Which Prosodic Features Matter Most for Pragmatics?—0
AI-Based IVR—0
Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech RecognitionCode0
Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching OptimizationCode3
WavLM model ensemble for audio deepfake detectionCode0
PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform GenerationCode3
SaSLaW: Dialogue Speech Corpus with Audio-visual Egocentric Information Toward Environment-adaptive Dialogue Speech SynthesisCode0
PRESENT: Zero-Shot Text-to-Prosody ControlCode1
VNet: A GAN-based Multi-Tier Discriminator Network for Speech Synthesis Vocoders—0
Bailing-TTS: Chinese Dialectal Speech Synthesis Towards Human-like Spontaneous Representation—0
Generative Expressive Conversational Speech SynthesisCode1
VoxSim: A perceptual voice similarity datasetCode1
Speech Bandwidth Expansion Via High Fidelity Generative Adversarial Networks—0
Towards Improving NAM-to-Speech Synthesis Intelligibility using Self-Supervised Speech Models—0
dMel: Speech Tokenization made SimpleCode1
Overview of Speaker Modeling and Its Applications: From the Lens of Deep Speaker Representation Learning—0
MSceneSpeech: A Multi-Scene Speech Dataset For Expressive Speech Synthesis—0
Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource SettingsCode1
Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models—0
Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and SynthesisCode2
Toward accessible comics for blind and low vision readers—0
Autoregressive Speech Synthesis without Vector Quantization—0
Analyzing Speech Unit Selection for Textless Speech-to-Speech Translation—0
Fine-Grained and Interpretable Neural Speech EditingCode1
CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic TokensCode11
FA-GAN: Artifacts-free and Phase-aware High-fidelity GAN-based Vocoder—0
We Need Variations in Speech Generation: Sub-center Modelling for Speaker Embeddings—0
Show:102550
← PrevPage 4 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