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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 181–190 of 332 papers

Title	Date	Tasks	Status	Hype
Extending Text-to-Speech Synthesis with Articulatory Movement Prediction using Ultrasound Tongue Imaging	Jul 12, 2021	PredictionSpeech Synthesis	CodeCode Available	0
Location, Location: Enhancing the Evaluation of Text-to-Speech Synthesis Using the Rapid Prosody Transcription Paradigm	Jul 6, 2021	Speech Synthesistext-to-speech	—Unverified	0
Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input	Jul 5, 2021	Speech Synthesistext-to-speech	CodeCode Available	0
WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis	Jun 17, 2021	Speech Synthesistext-to-speech	CodeCode Available	1
RyanSpeech: A Corpus for Conversational Text-to-Speech Synthesis	Jun 15, 2021	speech-recognitionSpeech Recognition	CodeCode Available	1
PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior	Jun 11, 2021	Audio GenerationDenoising	—Unverified	0
Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-based Multi-modal Context Modeling	Jun 11, 2021	Speech Synthesistext-to-speech	CodeCode Available	1
An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis	Jun 3, 2021	Speaker VerificationSpeech Synthesis	—Unverified	0
Speaker verification-derived loss and data augmentation for DNN-based multispeaker speech synthesis	Jun 3, 2021	Data AugmentationSpeaker Verification	—Unverified	0
RAD-TTS: Parallel Flow-Based TTS with Robust Alignment Learning and Diverse Synthesis	Jun 2, 2021	DiversityRhythm	CodeCode Available	1

Show:10 25 50

← PrevPage 19 of 34Next →

All datasets LJSpeech 20000 utterances CMUDict 0.7b HUI speech corpus Thorsten voice 21.02 neutral Trinity Speech-Gesture Dataset

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	NaturalSpeech	Audio Quality MOS	4.56	—	Unverified
2	VITS	Audio Quality MOS	4.43	—	Unverified
3	Grad-TTS + HiFiGAN (1000 steps)	Audio Quality MOS	4.37	—	Unverified
4	FastSpeech 2 + HiFiGAN	Audio Quality MOS	4.34	—	Unverified
5	Glow-TTS + HiFiGAN	Audio Quality MOS	4.34	—	Unverified
6	FastSpeech 2 + HiFiGAN	Audio Quality MOS	4.32	—	Unverified
7	FastDiff (4 steps)	Audio Quality MOS	4.28	—	Unverified
8	FastDiff-TTS	Audio Quality MOS	4.03	—	Unverified
9	Transformer TTS (Mel + WaveGlow)	Audio Quality MOS	3.88	—	Unverified
10	FastSpeech (Mel + WaveGlow)	Audio Quality MOS	3.84	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Mia	10-keyword Speech Commands dataset	16	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Token-Level Ensemble Distillation	Phoneme Error Rate	4.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Tacotron 2	Mean Opinion Score	3.74	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Tacotron 2	Mean Opinion Score	3.49	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Match-TTSG	MOS	3.7	—	Unverified