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

Showing 301332 of 332 papers

TitleStatusHype
Emphasized Accent Phrase Prediction from Text for Advertisement Text-To-Speech Synthesis0
Duration Modeling by Multi-Models based on Vowel Production characteristics0
Hippocratic Abbreviation Expansion0
RSS-TOBI - A Prosodically Enhanced Romanian Speech Corpus0
Towards Multilingual Conversations in the Medical Domain: Development of Multilingual Medical Data and A Network-based ASR System0
Using a machine learning model to assess the complexity of stress systems0
Designing Language Technology Applications: A Wizard of Oz Driven Prototyping Framework0
Predicting Romanian Stress Assignment0
HMM-based Mandarin Singing Voice Synthesis Using Tailored Synthesis Units and Question Sets0
Development of Marathi Part of Speech Tagger Using Statistical Approach0
Fast Bootstrapping of Grapheme to Phoneme System for Under-resourced Languages - Application to the Iban Language0
Russian Stress Prediction using Maximum Entropy Ranking0
Multi-step Natural Language Understanding0
WebWOZ: A Platform for Designing and Conducting Web-based Wizard of Oz Experiments0
Adaptive Parser-Centric Text Normalization0
Large tagset labeling using Feed Forward Neural Networks. Case study on Romanian Language0
Punjabi Text-To-Speech Synthesis System0
Automatically Acquiring Fine-Grained Information Status Distinctions in German0
Vers une annotation automatique de corpus audio pour la synth\`ese de parole (Towards Fully Automatic Annotation of Audio Books for Text-To-Speech (TTS) Synthesis) [in French]0
Variations prosodiques en synth\`ese par s\'election d'unit\'es: l'exemple des phrases interrogatives (Prosodic variations in unit-based speech synthesis: the example of interrogative sentences) [in French]0
Leveraging supplemental representations for sequential transduction0
Real-time Incremental Speech-to-Speech Translation of Dialogs0
Designing French Tale Corpora for Entertaining Text To Speech Synthesis0
LDC Forced Aligner0
BUCEADOR, a multi-language search engine for digital libraries0
Building Text-to-Speech Systems for Resource Poor Languages0
Learning Sentiment Lexicons in Spanish0
Texto4Science: a Quebec French Database of Annotated Short Text Messages0
Building a synchronous corpus of acoustic and 3D facial marker data for adaptive audio-visual speech synthesis0
Open-Source Boundary-Annotated Corpus for Arabic Speech and Language Processing0
Towards Fully Automatic Annotation of Audio Books for TTS0
BAD: An Assistant tool for making verses in Basque0
Show:102550
← PrevPage 7 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NaturalSpeechAudio Quality MOS4.56Unverified
2VITSAudio Quality MOS4.43Unverified
3Grad-TTS + HiFiGAN (1000 steps)Audio Quality MOS4.37Unverified
4FastSpeech 2 + HiFiGANAudio Quality MOS4.34Unverified
5Glow-TTS + HiFiGANAudio Quality MOS4.34Unverified
6FastSpeech 2 + HiFiGANAudio Quality MOS4.32Unverified
7FastDiff (4 steps)Audio Quality MOS4.28Unverified
8FastDiff-TTSAudio Quality MOS4.03Unverified
9Transformer TTS (Mel + WaveGlow)Audio Quality MOS3.88Unverified
10FastSpeech (Mel + WaveGlow)Audio Quality MOS3.84Unverified
#ModelMetricClaimedVerifiedStatus
1Mia10-keyword Speech Commands dataset16Unverified
#ModelMetricClaimedVerifiedStatus
1Token-Level Ensemble DistillationPhoneme Error Rate4.6Unverified
#ModelMetricClaimedVerifiedStatus
1Tacotron 2Mean Opinion Score3.74Unverified
#ModelMetricClaimedVerifiedStatus
1Tacotron 2Mean Opinion Score3.49Unverified
#ModelMetricClaimedVerifiedStatus
1Match-TTSGMOS3.7Unverified