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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/keonlee9420/STYLER
https://github.com/keonlee9420/StyleSpeech
https://github.com/keonlee9420/VAENAR-TTS
Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
https://github.com/keonlee9420/WaveGrad2
https://github.com/kingridda/voice-cloning-AI
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
https://github.com/komyeongjin/specdiff-gan
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/ksw0306/WaveVAE
https://github.com/lifeiteng/vall-e
Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
https://github.com/lmnt-com/wavegrad
https://github.com/lucidrains/voicebox-pytorch
Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
https://github.com/majidAdibian77/ResGrad
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/majidAdibian77/persian-SV2TTS
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
https://github.com/maum-ai/wavegrad2
https://github.com/merts1/dc_tts-turkish-implementation-T-rk-e-metinden-sese-
https://github.com/merts1/dc_tts-turkish-implementation-Turkce-metinden-sese-
https://github.com/mindmapper15/Voice-Converter
https://github.com/mindslab-ai/wavegrad2
https://github.com/ming024/FastSpeech2
https://github.com/mkotha/WaveRNN
https://github.com/modelscope/FunCodec
LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT
https://github.com/moonintheriver/neuralsvb
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism
https://github.com/mozilla/TTS
https://github.com/mtresearcher/FastSpeech2
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/mukeshv0/ParallelWaveGAN
https://github.com/multi-singer/multi-singer.github.io
Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus
https://github.com/ndk03/Accent-Preserving-Voice-Cloning-using-SV2TTS/tree/master/Speech-Modeling-master
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
https://github.com/ndkgit339/fastspeech2-filled_pause_speech_synthesis
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/noetits/ICE-Talk
https://github.com/oliverwatts/ophelia
https://github.com/openvpi/DiffSinger
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism
https://github.com/plachtaa/vall-e-x
Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
https://github.com/playvoice/grad-svc
Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
https://github.com/r9y9/deepvoice3_pytorch
https://github.com/r9y9/tacotron_pytorch
https://github.com/racai-ai/ROBINDialog
Tools and resources for Romanian text-to-speech and speech-to-text applications
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.