Papers with Code 아카이브
Audio Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 3
- 보존된 평가 기록
- 26
Audio generation (synthesis) is the task of generating raw audio such as speech.
<span style="color:grey; opacity: 0.6">( Image credit: MelNet )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/suno-ai/bark
https://github.com/swasun/VQ-VAE-Speech
https://github.com/tencent-ailab/fra-rir
FRA-RIR: Fast Random Approximation of the Image-source Method
https://github.com/tensorflow/magenta
https://github.com/text-to-audio/make-an-audio
Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models
https://github.com/thorwhalen/sla
https://github.com/thorwhalen/slang
https://github.com/tifgan/gacela
GACELA -- A generative adversarial context encoder for long audio inpainting
https://github.com/tigthor/Voice-Cloning-AI
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
https://github.com/ucsd-dsc-arts/dsc160-final-dsc160-final-group19
https://github.com/v-iashin/sparsesync
https://github.com/v-iashin/video_features
https://github.com/vicky-hnk/time-flex
https://github.com/vincentherrmann/pytorch-wavenet
https://github.com/voice-privacy-challenge/voice-privacy-challenge-2024
Anonymizing Speech: Evaluating and Designing Speaker Anonymization Techniques
https://github.com/wavlab-speech/versa
ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs for Audio, Music, and Speech
https://github.com/wavmark/wavmark
https://github.com/wilson1yan/VideoGPT
https://github.com/xingchensong/s3tokenizer
https://github.com/yangdongchao/text-to-sound-synthesis
Diffsound: Discrete Diffusion Model for Text-to-sound Generation
https://github.com/yebiny/DepthOfAnaesthesia_eeg
https://github.com/zassou65535/WaveGAN
https://github.com/zhangxinfd/speechtokenizer
https://github.com/zhong110020/Tensorflow-TCN
https://github.com/zhong110020/keras-tcn
https://github.com/zll1996/TCN
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.