Papers with Code 아카이브
Speech Synthesis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 15
- 평가표
- 5
- 보존된 평가 기록
- 31
Speech synthesis is the task of generating speech from some other modality like text, lip movements etc.
Please note that the leaderboards here are not really comparable between studies - as they use mean opinion score as a metric and collect different samples from Amazon Mechnical Turk.
<span style="color:grey; opacity: 0.6">( Image credit: WaveNet: A generative model for raw audio )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks
CleanUNet 2: A Hybrid Speech Denoising Model on Waveform and Spectrogram
Can large-scale vocoded spoofed data improve speech spoofing countermeasure with a self-supervised front end?
Cross-Utterance Conditioned VAE for Speech Generation
MuLanTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2023
BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network
Matcha-TTS: A fast TTS architecture with conditional flow matching
The FruitShell French synthesis system at the Blizzard 2023 Challenge
Towards Spontaneous Style Modeling with Semi-supervised Pre-training for Conversational Text-to-Speech Synthesis
QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation Learning
The DeepZen Speech Synthesis System for Blizzard Challenge 2023
Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with Disentangled Representations
SeamlessM4T: Massively Multilingual & Multimodal Machine Translation
TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition
Accurate synthesis of Dysarthric Speech for ASR data augmentation
AffectEcho: Speaker Independent and Language-Agnostic Emotion and Affect Transfer for Speech Synthesis
DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker Embedding
iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN
EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis
On Error Propagation of Diffusion Models
Adversarial Training of Denoising Diffusion Model Using Dual Discriminators for High-Fidelity Multi-Speaker TTS
Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation
SALTTS: Leveraging Self-Supervised Speech Representations for improved Text-to-Speech Synthesis
DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training
Audio-visual video-to-speech synthesis with synthesized input audio
Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech
METTS: Multilingual Emotional Text-to-Speech by Cross-speaker and Cross-lingual Emotion Transfer
Minimally-Supervised Speech Synthesis with Conditional Diffusion Model and Language Model: A Comparative Study of Semantic Coding
SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer
An analysis on the effects of speaker embedding choice in non auto-regressive TTS
SLMGAN: Exploiting Speech Language Model Representations for Unsupervised Zero-Shot Voice Conversion in GANs
Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis
On the Use of Self-Supervised Speech Representations in Spontaneous Speech Synthesis
Deep Speech Synthesis from MRI-Based Articulatory Representations
Disentanglement in a GAN for Unconditional Speech Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.