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 51–100 of 332 papers

TitleStatusHype
UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal PromptsCode1
Semi-supervised URL Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph EntitiesCode1
MnTTS2: An Open-Source Multi-Speaker Mongolian Text-to-Speech Synthesis DatasetCode1
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language ModelsCode1
Effective Deep Learning Models for Automatic Diacritization of Arabic TextCode1
EdiTTS: Score-based Editing for Controllable Text-to-SpeechCode1
ArTST: Arabic Text and Speech TransformerCode1
MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied BaselineCode1
Learning Arousal-Valence Representation from Categorical Emotion Labels of SpeechCode1
KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis DatasetCode1
WaveGrad: Estimating Gradients for Waveform GenerationCode1
Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech TranslationCode1
Imaginary Voice: Face-styled Diffusion Model for Text-to-SpeechCode1
WaveGrad 2: Iterative Refinement for Text-to-Speech SynthesisCode1
Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesisCode1
Automatic Prosody Annotation with Pre-Trained Text-Speech ModelCode1
Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech SynthesisCode1
Fine-grained style control in Transformer-based Text-to-speech SynthesisCode1
FastSpeech 2: Fast and High-Quality End-to-End Text to SpeechCode1
Exploring Transfer Learning for Low Resource Emotional TTSCode1
Grad-TTS: A Diffusion Probabilistic Model for Text-to-SpeechCode1
Accented Text-to-Speech Synthesis with a Conditional Variational AutoencoderCode1
In Other News: A Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited DataCode1
Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer LearningCode1
Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment SearchCode1
YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyoneCode1
Towards Lifelong Learning of Multilingual Text-To-Speech SynthesisCode0
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech SynthesisCode0
The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation SystemsCode0
Tools and resources for Romanian text-to-speech and speech-to-text applicationsCode0
Systematic Inequalities in Language Technology Performance across the World's LanguagesCode0
Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech SynthesisCode0
Systematic Inequalities in Language Technology Performance across the World’s LanguagesCode0
Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory InputCode0
PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive PriorCode0
Preparing an Endangered Language for the Digital Age: The Case of Judeo-SpanishCode0
Attentive Multi-Layer Perceptron for Non-autoregressive GenerationCode0
Spoofing Speaker Verification Systems with Deep Multi-speaker Text-to-speech SynthesisCode0
Voicebox: Text-Guided Multilingual Universal Speech Generation at ScaleCode0
Multimodal Latent Language Modeling with Next-Token DiffusionCode0
Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic ForgettingCode0
Non-Autoregressive Neural Text-to-SpeechCode0
Mlphon: A Multifunctional Grapheme-Phoneme Conversion Tool Using Finite State TransducersCode0
Meta Learning Text-to-Speech Synthesis in over 7000 LanguagesCode0
Effective parameter estimation methods for an ExcitNet model in generative text-to-speech systemsCode0
MIA-Prognosis: A Deep Learning Framework to Predict Therapy ResponseCode0
ECAPA-TDNN for Multi-speaker Text-to-speech SynthesisCode0
Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition ErrorsCode0
MelNet: A Generative Model for Audio in the Frequency DomainCode0
Investigation of enhanced Tacotron text-to-speech synthesis systems with self-attention for pitch accent languageCode0
Show:102550
← PrevPage 2 of 7Next →
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