Papers with Code 아카이브
Text-To-Speech Synthesis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 6
- 보존된 평가 기록
- 21
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Word-wise intonation model for cross-language TTS systems
Accent conversion using discrete units with parallel data synthesized from controllable accented TTS
StyleFusion TTS: Multimodal Style-control and Enhanced Feature Fusion for Zero-shot Text-to-speech Synthesis
StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion
Text-To-Speech Synthesis In The Wild
Full-text Error Correction for Chinese Speech Recognition with Large Language Model
SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis
What happens to diffusion model likelihood when your model is conditional?
AS-Speech: Adaptive Style For Speech Synthesis
Sample-Efficient Diffusion for Text-To-Speech Synthesis
kNN Retrieval for Simple and Effective Zero-Shot Multi-speaker Text-to-Speech
PRESENT: Zero-Shot Text-to-Prosody Control
Speech Bandwidth Expansion Via High Fidelity Generative Adversarial Networks
Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models
Autoregressive Speech Synthesis without Vector Quantization
Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis
Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization
FLY-TTS: Fast, Lightweight and High-Quality End-to-End Text-to-Speech Synthesis
Multi-Scale Accent Modeling and Disentangling for Multi-Speaker Multi-Accent Text-to-Speech Synthesis
EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech
VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment
Meta Learning Text-to-Speech Synthesis in over 7000 Languages
VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers
Autoregressive Diffusion Transformer for Text-to-Speech Synthesis
XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model
Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model
StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
Style Mixture of Experts for Expressive Text-To-Speech Synthesis
Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis
Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback
DLPO: Diffusion Model Loss-Guided Reinforcement Learning for Fine-Tuning Text-to-Speech Diffusion Models
Evaluating Text-to-Speech Synthesis from a Large Discrete Token-based Speech Language Model
UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts
RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis
PSCodec: A Series of High-Fidelity Low-bitrate Neural Speech Codecs Leveraging Prompt Encoders
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.