SOTAVerified

Text-To-Speech Synthesis

Text-To-Speech Synthesis is a machine learning task that involves converting written text into spoken words. The goal is to generate synthetic speech that sounds natural and resembles human speech as closely as possible.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 332 papers

TitleStatusHype
Grad-TTS: A Diffusion Probabilistic Model for Text-to-SpeechCode1
UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal PromptsCode1
Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment SearchCode1
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language ModelsCode1
Imaginary Voice: Face-styled Diffusion Model for Text-to-SpeechCode1
OverFlow: Putting flows on top of neural transducers for better TTSCode1
ArTST: Arabic Text and Speech TransformerCode1
Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer LearningCode1
Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech SynthesisCode1
Fine-grained style control in Transformer-based Text-to-speech SynthesisCode1
Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech RecognitionCode1
FastSpeech 2: Fast and High-Quality End-to-End Text to SpeechCode1
RWEN-TTS: Relation-aware Word Encoding Network for Natural Text-to-Speech SynthesisCode1
Automatic Prosody Annotation with Pre-Trained Text-Speech ModelCode1
End-to-End Adversarial Text-to-SpeechCode1
Enhancing Speech Intelligibility in Text-To-Speech Synthesis using Speaking Style ConversionCode1
Exploring Transfer Learning for Low Resource Emotional TTSCode1
Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided AttentionCode1
Effective Deep Learning Models for Automatic Diacritization of Arabic TextCode1
EdiTTS: Score-based Editing for Controllable Text-to-SpeechCode1
Accented Text-to-Speech Synthesis with a Conditional Variational AutoencoderCode1
Learning Arousal-Valence Representation from Categorical Emotion Labels of SpeechCode1
RAD-TTS: Parallel Flow-Based TTS with Robust Alignment Learning and Diverse SynthesisCode1
RyanSpeech: A Corpus for Conversational Text-to-Speech SynthesisCode1
Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-based Multi-modal Context ModelingCode1
Show:102550
← PrevPage 3 of 14Next →
All datasetsLJSpeech20000 utterancesCMUDict 0.7bHUI speech corpusThorsten voice 21.02 neutralTrinity Speech-Gesture Dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NaturalSpeechAudio Quality MOS4.56—Unverified
2VITSAudio Quality MOS4.43—Unverified
3Grad-TTS + HiFiGAN (1000 steps)Audio Quality MOS4.37—Unverified
4FastSpeech 2 + HiFiGANAudio Quality MOS4.34—Unverified
5Glow-TTS + HiFiGANAudio Quality MOS4.34—Unverified
6FastSpeech 2 + HiFiGANAudio Quality MOS4.32—Unverified
7FastDiff (4 steps)Audio Quality MOS4.28—Unverified
8FastDiff-TTSAudio Quality MOS4.03—Unverified
9Transformer TTS (Mel + WaveGlow)Audio Quality MOS3.88—Unverified
10FastSpeech (Mel + WaveGlow)Audio Quality MOS3.84—Unverified
#ModelMetricClaimedVerifiedStatus
1Mia10-keyword Speech Commands dataset16—Unverified
#ModelMetricClaimedVerifiedStatus
1Token-Level Ensemble DistillationPhoneme Error Rate4.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Tacotron 2Mean Opinion Score3.74—Unverified
#ModelMetricClaimedVerifiedStatus
1Tacotron 2Mean Opinion Score3.49—Unverified
#ModelMetricClaimedVerifiedStatus
1Match-TTSGMOS3.7—Unverified