SOTAVerified

Prosody Prediction

Predicting prosodic prominence from text. This is a 2-way classification task, assigning each word in a sentence a label 1 (prominent) or 0 (non-prominent).

( Image credit: Helsinki Prosody Corpus )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–15 of 15 papers

TitleStatusHype
On the Utility of Self-supervised Models for Prosody-related TasksCode1
PRESENT: Zero-Shot Text-to-Prosody ControlCode1
Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word RepresentationsCode0
Prosody Analysis of AudiobooksCode0
Ensemble prosody prediction for expressive speech synthesis—0
Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesis—0
Learning Multilingual Expressive Speech Representation for Prosody Prediction without Parallel Data—0
Prosody Learning Mechanism for Speech Synthesis System Without Text Length Limit—0
VisualSpeech: Enhance Prosody with Visual Context in TTS—0
What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model—0
A Comparative Analysis of Pretrained Language Models for Text-to-Speech—0
Word-wise intonation model for cross-language TTS systems—0
Automatic Prosody Prediction for Chinese Speech Synthesis using BLSTM-RNN and Embedding Features—0
Controllable Sequence-To-Sequence Neural TTS with LPCNET Backend for Real-time Speech Synthesis on CPU—0
DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles—0
Show:102550

No leaderboard results yet.