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/bfs18/rfwave
공식 코드RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction
https://github.com/chomeyama/DualCycleGAN
공식 코드Nonparallel High-Quality Audio Super Resolution with Domain Adaptation and Resampling CycleGANs
https://github.com/chrisdonahue/wavegan
공식 코드https://github.com/ciaua/score_lyrics_free_svg
공식 코드https://github.com/ciaua/unagan
공식 코드Unconditional Audio Generation with Generative Adversarial Networks and Cycle Regularization
https://github.com/cyanbx/Frieren-V2A
공식 코드Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching
https://github.com/cyrusvahidi/jtfs-gpu
공식 코드https://github.com/cyrusvahidi/kymatio-wavespin
공식 코드https://github.com/dcase2024-task7-sound-scene-synthesis/fadtk
공식 코드Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation
https://github.com/declare-lab/TangoFlux
공식 코드https://github.com/declare-lab/tango
공식 코드Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model
https://github.com/deep-privacy/SA-toolkit
공식 코드Anonymizing Speech: Evaluating and Designing Speaker Anonymization Techniques
https://github.com/descriptinc/descript-audio-codec
공식 코드https://github.com/digitalphonetics/ims-toucan
공식 코드https://github.com/dinhoitt/bemaganv2
공식 코드BemaGANv2: A Tutorial and Comparative Survey of GAN-based Vocoders for Long-Term Audio Generation
https://github.com/divelab/dilated
공식 코드https://github.com/f90/Seq-U-Net
공식 코드Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling
https://github.com/facebookresearch/audioseal
공식 코드Proactive Detection of Voice Cloning with Localized Watermarking
https://github.com/facebookresearch/demucs
공식 코드https://github.com/facebookresearch/moviegenbench
공식 코드https://github.com/fisheggg/lvns-rave
공식 코드LVNS-RAVE: Diversified audio generation with RAVE and Latent Vector Novelty Search
https://github.com/funaudiollm/cosyvoice
공식 코드https://github.com/funaudiollm/inspiremusic
공식 코드https://github.com/galaxycong/styledubber
공식 코드StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing
https://github.com/galgreshler/Catch-A-Waveform
공식 코드Catch-A-Waveform: Learning to Generate Audio from a Single Short Example
https://github.com/gariscat/loopy
공식 코드LooPy: A Research-Friendly Mix Framework for Music Information Retrieval on Electronic Dance Music
https://github.com/gwh22/LAFMA
공식 코드LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation
https://github.com/haoheliu/AudioLDM
공식 코드AudioLDM: Text-to-Audio Generation with Latent Diffusion Models
https://github.com/haoheliu/AudioLDM2
공식 코드AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining
https://github.com/haoheliu/ssr_eval
공식 코드https://github.com/happylittlecat2333/Auffusion
공식 코드Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation
https://github.com/hashim19/Rob-ASD
공식 코드https://github.com/hazyresearch/state-spaces
공식 코드https://github.com/heng-hw/V2A-Mapper
공식 코드V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models
https://github.com/hhguo/EA-SVC
공식 코드Phonetic Posteriorgrams based Many-to-Many Singing Voice Conversion via Adversarial Training
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.