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 401–450 of 1249 papers

TitleStatusHype
Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis—0
Probing the Feasibility of Multilingual Speaker Anonymization—0
Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization—0
A Comprehensive Survey on Diffusion Models and Their Applications—0
Lightweight Zero-shot Text-to-Speech with Mixture of Adapters—0
FLY-TTS: Fast, Lightweight and High-Quality End-to-End Text-to-Speech Synthesis—0
Leveraging Parameter-Efficient Transfer Learning for Multi-Lingual Text-to-Speech Adaptation—0
High Fidelity Text-to-Speech Via Discrete Tokens Using Token Transducer and Group Masked Language Model—0
Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment—0
Towards Zero-Shot Text-To-Speech for Arabic Dialects—0
One-Class Learning with Adaptive Centroid Shift for Audio Deepfake DetectionCode0
A multi-speaker multi-lingual voice cloning system based on vits2 for limmits 2024 challenge—0
A Mel Spectrogram Enhancement Paradigm Based on CWT in Speech Synthesis—0
1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis—0
Multi-Scale Accent Modeling and Disentangling for Multi-Speaker Multi-Accent Text-to-Speech Synthesis—0
ToneUnit: A Speech Discretization Approach for Tonal Language Speech Synthesis—0
PolySpeech: Exploring Unified Multitask Speech Models for Competitiveness with Single-task Models—0
VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment—0
CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems—0
Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?—0
Meta Learning Text-to-Speech Synthesis in over 7000 Languages—0
JenGAN: Stacked Shifted Filters in GAN-Based Speech Synthesis—0
Text-aware and Context-aware Expressive Audiobook Speech Synthesis—0
VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers—0
Autoregressive Diffusion Transformer for Text-to-Speech Synthesis—0
Spectral Codecs: Improving Non-Autoregressive Speech Synthesis with Spectrogram-Based Audio Codecs—0
Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model—0
Style Mixture of Experts for Expressive Text-To-Speech Synthesis—0
Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis—0
Accent Conversion in Text-To-Speech Using Multi-Level VAE and Adversarial Training—0
Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback—0
Multilingual Prosody Transfer: Comparing Supervised & Transfer Learning—0
DLPO: Diffusion Model Loss-Guided Reinforcement Learning for Fine-Tuning Text-to-Speech Diffusion Models—0
Evaluating Text-to-Speech Synthesis from a Large Discrete Token-based Speech Language Model—0
Expressivity and Speech Synthesis—0
Retrieval-Augmented Audio Deepfake Detection—0
Parameter Efficient Fine Tuning: A Comprehensive Analysis Across Applications—0
RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis—0
PSCodec: A Series of High-Fidelity Low-bitrate Neural Speech Codecs Leveraging Prompt Encoders—0
Leveraging the Interplay Between Syntactic and Acoustic Cues for Optimizing Korean TTS Pause Formation—0
Removing Speaker Information from Speech Representation using Variable-Length Soft Pooling—0
Humane Speech Synthesis through Zero-Shot Emotion and Disfluency GenerationCode0
Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator—0
M^3AV: A Multimodal, Multigenre, and Multipurpose Audio-Visual Academic Lecture Dataset—0
An Empirical Study of Speech Language Models for Prompt-Conditioned Speech Synthesis—0
EM-TTS: Efficiently Trained Low-Resource Mongolian Lightweight Text-to-Speech—0
Towards Accurate Lip-to-Speech Synthesis in-the-Wild—0
VoxGenesis: Unsupervised Discovery of Latent Speaker Manifold for Speech Synthesis—0
Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data—0
Towards Decoding Brain Activity During Passive Listening of SpeechCode0
Show:102550
← PrevPage 9 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