Papers with Code 아카이브
Prosody Prediction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 4
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).
<span style="color:grey; opacity: 0.6">( Image credit: Helsinki Prosody Corpus )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles
Word-wise intonation model for cross-language TTS systems
PRESENT: Zero-Shot Text-to-Prosody Control
Prosody Analysis of Audiobooks
A Comparative Analysis of Pretrained Language Models for Text-to-Speech
Learning Multilingual Expressive Speech Representation for Prosody Prediction without Parallel Data
What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model
Ensemble prosody prediction for expressive speech synthesis
Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesis
On the Utility of Self-supervised Models for Prosody-related Tasks
Prosody Learning Mechanism for Speech Synthesis System Without Text Length Limit
Controllable Sequence-To-Sequence Neural TTS with LPCNET Backend for Real-time Speech Synthesis on CPU
Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations
Automatic Prosody Prediction for Chinese Speech Synthesis using BLSTM-RNN and Embedding Features
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.