genmusic_demo_list

A list of demo websites for automatic music generation research

텍스트를 음악/오디오로 변환

• 다중 측면 컨디셔닝(확산; maman24): https://benadar293.github.io/multi-aspect-conditioning/
• 프레스토(확산; novac24arxiv): https://presto-music.github.io/web/
• MMGen(확산; wei24arxiv): https://awesome-mmgen.github.io/
• Seed-Music(확산+변환기; bai24arxiv): https://team.doubao.com/en/special/seed-music
• SongCreator(확산; lei24arxiv): https://songcreator.github.io/
• MSLDM(확산; xu24arxiv): https://xzwy.github.io/MSLDMDemo/
• 멀티 트랙 MusicLDM(확산; karchkhadze24arxiv): https://mt-musicldm.github.io/
• FluxMusic(확산; fei24arxiv): https://github.com/feizc/FluxMusic
• 제어-전송-확산(확산; demerlé24ismir): https://nilsdem.github.io/control-transfer-diffusion/
• AP 어댑터(확산; tsai24arxiv): https://rebrand.ly/AP-adapter
• MusiConGen(변환기; lan24arxiv): https://musicongen.github.io/musicongen_demo/
• 안정적인 오디오 개방형(확산; evans24arxiv): https://stability-ai.github.io/stable-audio-open-demo/
• MEDIC(확산; liu24arxiv): https://medic-zero.github.io/
• MusicGenStyle(변압기; rouard24ismir): https://musicgenstyle.github.io/
• MelodyFlow(변환기+확산; lelan24arxiv): https://melodyflow.github.io/
• MelodyLM(변압기+확산; li24arxiv): https://melodylm666.github.io/
• JASCO(흐름; tal24ismir): https://pages.cs.huji.ac.il/adiyoss-lab/JASCO/
• MusicFlow(확산; prajwal24icml): 해당 없음
• Diff-A-Riff(확산; nistal24ismir): https://sonycslparis.github.io/diffariff-companion/
• DITTO-2(확산; novac24ismir): https://ditto-music.github.io/ditto2/
• SoundCTM(확산; saito24arxiv): 해당 없음
• Instruct-MusicGen(변환기; zhang24arxiv): https://foul-ice-5ea.notion.site/Instruct-MusicGen-Demo-Page-Under-construction-a1e7d8d474f74df18bda9539d96687ab
• QA-MDT(확산; li24arxiv): https://qa-mdt.github.io/
• 안정적인 오디오 2(확산; evans24ismir): https://stability-ai.github.io/stable-audio-2-demo/
• 멜로디스트(변압기; hong24arxiv): https://text2songmelodist.github.io/Sample/
• SMITIN(변압기; koo24arxiv): https://wide-wood-512.notion.site/SMITIN-Self-Monitored-Inference-Time-INtervention-for-Generative-Music-Transformers-Demo-Page-983723e6e9ac4f008298f3c427a23241
• 안정적인 오디오(확산; evans24arxiv): https://stability-ai.github.io/stable-audio-demo/
• MusicMagus(확산; zhang24ijcai): https://wry-neighbor-173.notion.site/MusicMagus-Zero-Shot-Text-to-Music-Editing-via-Diffusion-Models-8f55a82f34944eb9a4028ca56c546d9d
• DITTO(확산; novac24arxiv): https://ditto-music.github.io/web/
• MAGNeT(변압기; ziv24arxiv): https://pages.cs.huji.ac.il/adiyoss-lab/MAGNeT/
• 머스탱고(확산; melechovsky24naacl): https://github.com/AMAAI-Lab/mustango
• 뮤직 컨트롤넷(확산; wu24taslp): https://musiccontrolnet.github.io/web/
• InstrumentGen(변압기, nercessian23ml4audio): https://instrumentgen.netlify.app/
• Coco-Mulla(변환기; lin23arxiv): https://kikyo-16.github.io/coco-mulla/
• JEN-1 작곡가(확산; yao23arxiv): https://www.jenmusic.ai/audio-demos
• UniAudio(변압기; yang23arxiv): http://dongchaoyang.top/UniAudio_demo/
• MusicLDM(확산; chen23arxiv): https://musicldm.github.io/
• InstructME(확산; han23arxiv): https://musicedit.github.io/
• JEN-1(확산; li23arxiv): https://www.futureverse.com/research/jen/demos/jen1
• MusicGen(Transformer; copet23arxiv): https://ai.honu.io/papers/musicgen/
• MeLoDy(Transformer+diffusion; lam23arxiv): https://efficient-melody.github.io/
• MusicLM(Transformer; agostinelli23arxiv): https://google-research.github.io/seanet/musiclm/examples/
• Noise2Music(확산; huang23arxiv): https://noise2music.github.io/
• ERNIE-음악(확산; zhu23arxiv): 해당 없음
• 리퓨전(diffusion;): https://www.riffusion.com/

텍스트를 오디오로

• MambaFoley(mamba; xie24arxiv): 해당 없음
• PicoAudio(확산; xie24arxiv): https://zeyuxie29.github.io/PicoAudio.github.io/
• AudioLCM(확산; liu24arxiv): https://audiolcm.github.io/
• UniAudio 1.5(변환기; yang24arxiv): https://github.com/yangdongchao/LLM-Codec
• 탱고 2 (확산; majumder24mm): https://tango2-web.github.io/
• 배턴 (확산; liao24arxiv): https://baton2024.github.io/
• T-FOLEY(확산; chung24icassp): https://yoonjinxd.github.io/Event-guided_FSS_Demo.github.io/
• 오디오박스(확산; vyas23arxiv): https://audiobox.metademolab.com/
• 암피온(zhang23arxiv): https://github.com/open-mmlab/Amphion
• VoiceLDM(확산; lee23arxiv): https://voiceldm.github.io/
• AudioLDM 2(확산; liu23arxiv): https://audioldm.github.io/audioldm2/
• WavJourney(; liu23arxiv): https://audio-agi.github.io/WavJourney_demopage/
• CLIPSynth(확산; dong23cvprw): https://salu133445.github.io/clipsynth/
• CLIPSonic (확산; dong23waspaa): https://salu133445.github.io/clipsonic/
• SoundStorm(Transformer; borsos23arxiv): https://google-research.github.io/seanet/soundstorm/examples/
• 감사(확산; wang23arxiv): https://audit-demo.github.io/
• VALL-E(Transformer; wang23arxiv): https://www.microsoft.com/en-us/research/project/vall-e/(연설용)
• 다중 소스 확산 모델(확산; 23arxiv): https://gladia-research-group.github.io/multi-source-diffusion-models/
• Make-An-Audio(확산; huang23arxiv): https://text-to-audio.github.io/(일반 사운드용)
• AudioLDM(확산; liu23arxiv): https://audioldm.github.io/(일반 사운드용)
• AudioGen(Transformer; kreuk23iclr): https://felixkreuk.github.io/audiogen/(일반 사운드용)
• AudioLM(Transformer; borsos23taslp): https://google-research.github.io/seanet/audiolm/examples/(일반 사운드용)

텍스트를 미디로

• text2midi(변환기; bhandari25aaai): https://huggingface.co/spaces/amaai-lab/text2midi
• MuseCoco(변압기, lu23arxiv): https://ai-muzic.github.io/musecoco/

오디오 도메인 음악 생성

• VampNet(변압기; garcia23ismir): https://hugo-does-things.notion.site/VampNet-Music-Generation-via-Masked-Acoustic-Token-Modeling-e37aabd0d5f1493aa42c5711d0764b33
• 빠른 주크박스(주크박스+지식 증류; pezzat-morales23mdpi): https://soundcloud.com/michel-pezzat-615988723
• DAG(확산; pascual23icassp): https://diffusionaudiosynesis.github.io/
• 뮤직카! (GAN; pasini22ismir): https://huggingface.co/spaces/marcop/musika
• JukeNox(VQVAE+Transformer; dhariwal20arxiv): https://openai.com/blog/jukebox/
• UNAGAN(GAN; liu20arxiv): https://github.com/ciaua/unagan
• dadabots(sampleRNN; carr18mume): http://dadabots.com/music.php

주어진 노래, 반주 생성

• Llambada(변압기; trinh24arxiv): https://songgen-ai.github.io/llambada-demo/
• FastSAG(확산; chen24arxiv): https://fastsag.github.io/
• SingSong(VQVAE+Transofmrer; donahue23arxiv): https://storage.googleapis.com/sing-song/index.html

드럼 없는 오디오가 주어지면 드럼 반주 생성

• JukeDrummer(VQVAE+Transofmrer; wu22ismir): https://legoodmanner.github.io/jukedrummer-demo/

오디오 도메인 노래 합성

• InstructSing(ddsp; zeng24slt): https://wavelandspeech.github.io/instructsing/
• 프리스타일러(변압기; ning24arxiv): https://nzqian.github.io/Freestyler/
• Prompt-Singer(변압기; wang24naacl): https://prompt-singer.github.io/
• StyleSinger (확산; zhang24aaai): https://stylesinger.github.io/
• BiSinger(변압기; zhou23asru): https://bisinger-svs.github.io/
• HiddenSinger(확산; hwang23arxiv): https://jisang93.github.io/hiddensinger-demo/
• Make-A-Voice(변압기; huang23arxiv): https://make-a-voice.github.io/
• RMSSinger(확산; he23aclf): https://rmssinger.github.io/
• NaturalSpeech 2(확산; shen23arxiv): https://speechresearch.github.io/naturalspeech2/
• NANSY++(변환기; choi23iclr): https://bald-lifeboat-9af.notion.site/Demo-Page-For-NANSY-67d92406f62b4630906282117c7f0c39
• UniSyn (; lei23aaai): https://leiyi420.github.io/UniSyn/
• VISinger 2(zhang22arxiv): https://zhangyongmao.github.io/VISinger2/
• xiaoicesing 2(Transformer+GAN; wang22arxiv): https://wavelandspeech.github.io/xiaoice2/
• WeSinger 2(Transformer+GAN; zhang22arxiv): https://zzw922cn.github.io/wesinger2/
• 유싱어(트랜스포머; kim22arxiv): https://u-singer.github.io/
• 싱잉타코트론(Transformer; wang22arxiv): https://hairuo55.github.io/SingingTacotron/
• KaraSinger(GRU/Transformer; liao22icassp): https://jerrygood0703.github.io/KaraSinger/
• VISinger(흐름; zhang2): https://zhangyongmao.github.io/VISinger/
• MLP 가수(믹서 블록, tae21arxiv): https://github.com/neosapience/mlp-singer
• LiteSing(wavenet; zhuang21icassp): https://auzxb.github.io/LiteSing/
• DiffSinger(확산; liu22aaai)[기간 모델링 없음]: https://diffsinger.github.io/
• HiFiSinger(변압기; chen20arxiv): https://speechresearch.github.io/hifisinger/
• DeepSinger(변압기; ren20kdd): https://speechresearch.github.io/deepsinger/
• xiaoice-멀티 가수: https://jiewu-demo.github.io/INTERSPEECH2020/
• 샤오아이싱: https://xiaoicesing.github.io/
• 바이트싱: https://bytesings.github.io/
• 멜로트론: https://nv-adlr.github.io/Mellotron
• Lee의 모델(lee19arxiv): http://ksinging.mystrikingly.com/
• http://home.ustc.edu.cn/~yiyh/interspeech2019/

오디오 도메인 가창 스타일 전송 / 가창 음성 변환

• ROSVC(; takahashi22arxiv): https://t-naoya.github.io/rosvc/
• DiffSVC(확산; liu21asru): https://liusongxiang.github.io/diffsvc/
• FastSVC(CNN; liu21icme): https://nobody996.github.io/FastSVC/
• SoftVC VITS(): https://github.com/svc-develop-team/so-vits-svc
• Assem-VC(;kim21nipsw): https://mindslab-ai.github.io/assem-vc/singer/
• iZotope-SVC(conv-encoder/decoder; nercessian20ismir): https://sites.google.com/izotope.com/ismir2020-audio-demo
• VAW-GAN(GAN; lu20arxiv): https://kunzhou9646.github.io/singvaw-gan/
• 폴리악20인터스피치(GAN; 폴리악20인터스피치): https://singing-conversion.github.io/
• SINGAN(GAN; sisman19apsipa): 해당 없음
• [MSVC-GAN] (GAN): https://hujinsen.github.io/
• https://mtg.github.io/singing-synesis-demos/voice-cloning/
• https://enk100.github.io/Unsupervised_Singing_Voice_Conversion/
• 용&남 (DSP; yong18icassp): https://seyong92.github.io/singing-expression-transfer/
• 사이베건(CNN+GAN; wu18faim): http://mirlab.org/users/haley.wu/cybegan/

오디오 도메인 음성-노래 변환

• AlignSTS(인코더/어댑터/aligner/diff-decoder; li23facl): https://alignsts.github.io/
• speech2sing2(GAN; wu20interspeech): https://ericwudayi.github.io/Speech2Singing-DEMO/
• speech2sing(인코더/디코더; parekh20icassp): https://jayneelparekh.github.io/icassp20/

오디오 영역 노래 교정

• 딥 오토튜너(CGRU; wagner19icassp): http://homes.sice.indiana.edu/scwager/deepautotuner.html

오디오 도메인 스타일 전송(일반)

• WaveTransfer(확산; baoueb24mlsp): https://wavetransfer.github.io/
• MusicTI(확산; li24aaai): https://lsfhuihuiff.github.io/MusicTI/
• DiffTransfer(확산; comanducci23ismir): https://lucacoma.github.io/DiffTransfer/
• RAVE-Latent Diffusion(확산;): https://github.com/moiseshorta/RAVE-Latent-Diffusion
• RAVE(VAE;caillon21arxiv): https://anonymous84654.github.io/RAVE_anonymous/; https://github.com/acids-ircam/RAVE
• VAE-GAN(VAE-GAN; bonnici22ijcnn): https://github.com/RussellSB/tt-vae-gan
• VQ-VAE(VQ-VAE; cifka21icassp): https://adasp.telecom-paris.fr/rc/demos_companion-pages/cifka-ss-vq-vae/
• MelGAN-VC(GAN; pasini19arxiv): https://www.youtube.com/watch?v=3BN577LK62Y&feature=youtu.be
• RaGAN(GAN; lu19aaai): https://github.com/ChienYuLu/Play-As-You-Like-Timbre-Enhanced-Multi-modal-Music-Style-Transfer
• TimbreTron(GAN; huang19iclr): https://www.cs.toronto.edu/~huang/TimbreTron/samples_page.html
• string2woodwind(DSP; wagner17icassp): http://homes.sice.indiana.edu/scwager/css.html

TTS

• NaturalSpeech 3(확산; ju24arxiv): https://speechresearch.github.io/naturalspeech3/
• VITS(변환기+흐름+GAN; kim21icml): https://github.com/jaywalnut310/vits

음성 음성 변환 / 음성 복제

• Applio (): https://github.com/IAHispano/Applio

보코더(일반)

• MusicHiFi(GAN+확산; zhu24arxiv): https://musichifi.github.io/web/
• BigVGAN(GAN; lee23iclr): https://bigvgan-demo.github.io/
• HifiGAN(GAN; kong20neurips): https://jik876.github.io/hifi-gan-demo/
• DiffWave (확산; kong21iclr): https://diffwave-demo.github.io/
• 병렬 WaveGAN(GAN; yamamoto20icassp): https://r9y9.github.io/projects/pwg/
• MelGAN(GAN; kumar19neurips): https://melgan-neurips.github.io/

보코더(노래)

• 골프(DDSP; yu23ismir): https://yoyolicon.github.io/golf-demo/
• DSPGAN(GAN; song23icassp): https://kunsung.github.io/DSPGAN/
• Sifi-GAN(GAN; yoneyama23icassp): https://chomeyama.github.io/SiFiGAN-Demo/
• SawSing(DDSP; wu22ismir): https://ddspvocoder.github.io/ismir-demo/
• 멀티싱어(wavenet; huang21mm): https://multi-singer.github.io/
• SingGAN(GAN; chen21arxiv): https://singgan.github.io/

오디오 토큰화

• 개선된 RVQGAN(VQ; kumar23arxiv): https://descript.notion.site/Descript-Audio-Codec-11389fce0ce2419891d6591a68f814d5
• HiFi 코덱(VQ; yang23arxiv): https://github.com/yangdongchao/AcademiCodec
• EnCodec(VQ; défossez22arxiv): https://github.com/facebookresearch/encodec
• SoundStream(VQ; zeghidour21arxiv): https://google-research.github.io/seanet/soundstream/examples/

오디오 초해상도

• AudioSR(확산; liu23arxiv): https://audioldm.github.io/audiosr/

오디오 도메인 루프 생성

• PJLoopGAN(GAN; yeh22ismir): https://arthurddd.github.io/PjLoopGAN/
• LoopGen(GAN; hang21ismir): https://loopgen.github.io/

주어진 점수, 음악 오디오 생성(연주): 피아노만

• TTS 기반 MIDI-오디오(Transformer-TTS; shi23icassp): https://nii-yamagishilab.github.io/sample-midi-to-audio/
• Wave2Midi2Wave(변압기+wavenet; hawthorne19iclr): https://magenta.tensorflow.org/maestro-wave2midi2wave
• BasisMixer(RNN+FFNN; chacon16ismir-lbd): https://www.youtube.com/watch?v=zdU8C6Su3TI

주어진 점수, 음악 오디오 생성(연주): 피아노(MIDI-to-audio라고도 함)에 국한되지 않음

• 딥 퍼포머(Transformer; dong22icassp): https://salu133445.github.io/deepperformer/
• PerformanceNet(CNN+GAN; wang19aaai): https://github.com/bwang514/PerformanceNet
• 조건부 Wavenet(Wavenet; manzelli18ismir): http://people.bu.edu/bkulis/projects/music/index.html

오디오/음색 합성

• gen-inst(변압기; nercessian24ismir): https://gen-inst.netlify.app/
• GANStrument(narita22arxiv): https://ganstrument.github.io/ganstrument-demo/
• NEWT(DDSP; hayes21ismir): https://benhayes.net/projects/nws/
• CRASH(확산; rouard21ismir): https://crash-diffusion.github.io/crash/
• DarkGAN(GAN; nital21ismir): https://an-1673.github.io/DarkGAN.io/
• MP3net(GAN; broek21arxiv): https://korneelvdbroek.github.io/mp3net/
• Michelashvili(dsp에서 영감을 받은; michelashvili20iclr): https://github.com/mosheman5/timbre_painting
• GAAE(GAN+AAE; haque20arxiv): https://drive.google.com/drive/folders/1et_BuZ_XDMrdsYzZDprLvEpmmuZrJ7jk
• MANNe(): https://github.com/JTColonel/manne
• DDSP(dsp에서 영감을 받은; lamtharn20iclr): https://storage.googleapis.com/ddsp/index.html
• MelNet(자동 회귀, vasquez19arxiv): https://audio-samples.github.io/
• AdVoc(; neekhara19arxiv): http://chrisdonahue.com/advoc_examples/
• GANSynth(CNN+GAN; engel19iclr): https://magenta.tensorflow.org/gansynth
• SynthNet(schimbinschi19ijcai): https://www.dropbox.com/sh/hkp3o5xjyexp2x0/AADvrfXTbHBXs9W7GN6Yeorua?dl=0
• TiFGAN(CNN+GAN; marafioti19arxiv): https://tifgan.github.io/
• 노래(defossez18nips): https://research.fb.com/wp-content/themes/fb-research/research/sing-paper/
• WaveGAN(CNN+GAN; donahue19iclr): https://github.com/chrisdonahue/wavegan
• WaveNet 자동 인코더(WaveNet; engel17arxiv): https://magenta.tensorflow.org/nsynth

이미지-음악/오디오

• Art2Mus(확산; rinaldi24ai4va): https://drive.google.com/drive/u/1/folders/1dHBxLWnyBqhVMJgUkTk0hKnFbGDVhw__
• MeLFusion(확산; chowdhury24cvpr): https://schowdhury671.github.io/melfusion_cvpr2024/
• Vis2Mus(인코더/디코더; zhang22arxiv): https://github.com/ldzhangyx/vis2mus
• ConchShell(인코더/디코더, fan22arxiv): 해당 없음

비디오-음악/오디오

• SONIQUE(확산; zhang24arxiv): https://github.com/zxxwxyyy/sonique
• Herrmann-1(LLM+변환기; haseeb24icassp): https://audiomatic-research.github.io/herrmann-1/
• Diff-BGM(확산; li24cvpr): https://github.com/sizhelee/Diff-BGM
• Frieren(확산; wang24arxiv): https://frieren-v2a.github.io/
• Video2Music(변압기; kang23arxiv): https://github.com/AMAAI-Lab/Video2Music
• 로리스(확산; yu23icml): https://justinyuu.github.io/LORIS/

대화형 멀티트랙 음악 작곡

• Yating을 통한 전파 방해(RNN; hsiao19ismir-lbd): https://www.youtube.com/watch?v=9ZIJrr6lmHg

인터랙티브 피아노 구성

• 피아노 지니(RNN; donahue18nips-creativity): https://piano-genie.glitch.me/
• AI 듀엣(RNN; roberts16nips-demo): https://experiments.withgoogle.com/ai/ai-duet/view/

대화형 모노럴 음악 작곡

• [뮤지컬스피치] (Transformer; d'Eon20nips-demo): https://jasondeon.github.io/musicalSpeech/

멜로디를 작곡하다

• MelodyT5(변압기, wu24ismir): https://github.com/sanderwood/melodyt5
• MelodyGLM(변압기; wu23arxiv): https://nextlab-zju.github.io/melodyglm/
• TunesFormer(변압기; wu23arxiv): https://github.com/sander-wood/tunesformer
• MeloForm(변압기, lu22arxiv): https://ai-muzic.github.io/meloform/
• parkR(markov; frieler22tismir): https://github.com/klausfrieler/parkR
• xai-lsr(VAE; bryankinns21nipsw): https://xai-lsr-ui.vercel.app/
• Trans-LSTM(Transformer+LSTM; dai21ismir): 해당 없음...
• 확산(diffusion+musicVAE; mittal21ismir): https://storage.googleapis.com/magentadata/papers/symbolic-music-diffusion/index.html
• MELONS(변압기; zhou21arxiv): https://yiathena.github.io/MELONS/
• 스케치넷(VAE+GRU; chen20ismir): https://github.com/RetroCirce/Music-SketchNet
• SSMGAN(VAE+LSTM+GAN; jhamtani19ml4md): https://drive.google.com/drive/folders/1TlOrbYAm7vGUvRrxa-uiH17bP-4N4e9z
• StructureNet(LSTM; medeot18ismir) https://www.dropbox.com/sh/yxkxlnzi913ba50/AAA_mDbhdmaGJC9qj0zSlqCea?dl=0
• MusicVAE(LSTM+VAE; roberts18icml): https://magenta.tensorflow.org/music-vae
• MidiNet(CNN+GAN; yang17ismir): https://richardyang40148.github.io/TheBlog/midinet_arxiv_demo.html
• C-RNN-GAN(LSTM+GAN, mogren16cml): http://mogren.one/publications/2016/c-rnn-gan/
• folkRNN(LSTM): https://folkrnn.org/

싱글 트랙 피아노 음악 작곡

• MusicMamba(mamba; chen24arxiv): 해당 없음
• EMO-Disentanger(변압기; huang24ismir): https://emo-disentanger.github.io/
• MuseBarControl(변압기; shu24arxiv): https://ganperf.github.io/musebarcontrol.github.io/musebarcontrol/
• WholeSong (확산; 24iclr): https://wholesonggen.github.io/
• MGM(변압기; 24tmm): https://github.com/hu-music/MGM
• 폴리퓨전(확산; min23ismir): https://polyffusion.github.io/
• EmoGen(변압기; kang23arxiv): https://ai-muzic.github.io/emogen/
• 작성 및 장식(Transformer; wu22arxiv): https://drive.google.com/drive/folders/1Y7HfExAz3PpPbFl0OnccxYDNF1KZUP-3
• 테마 변환기(Transformer; shih21arxiv): https://atosystem.github.io/ThemeTransformer/
• EMOPIA(변압기; hang21ismir): https://annahung31.github.io/EMOPIA/
• Dadagp(변압기; sarmento21ismir): https://drive.google.com/drive/folders/1USNH8olG9uy6vodslM3iXInBT725zult
• CP Transformer(변압기; hsiao21aaai): https://ailabs.tw/human-interaction/compound-word-transformer-generate-pop-piano-music-of-full-song-length/
• PIANOTREE VAE(VAE+GRU; wang20ismir): https://github.com/ZZWaang/PianoTree-VAE
• 기타 트랜스포머(Transformer; chen20ismir): https://ss12f32v.github.io/Guitar-Transformer-Demo/
• 팝 뮤직 트랜스포머(Transformer; huang20mm): https://github.com/YatingMusic/remi
• 조건부 음악 변환기(Transformer; choi19arxiv): https://storage.googleapis.com/magentadata/papers/music-transformer-autoencoder/index.html; 및 https://magenta.tensorflow.org/transformer-autoencoder
• PopRNN(RNN; yeh19ismir-lbd): https://soundcloud.com/yating_ai/sets/ismir-2019-submission/
• VGMIDI(LSTM; ferreira19ismir): https://github.com/lucasnfe/music-sentneuron
• 아마데우스(LSTM+RL; kumar19arxiv): https://goo.gl/ogVMSq
• 모듈화된 VAE(GRU+VAE; wang19icassp): https://github.com/MiuLab/MVAE_Music
• BachProp(GRU; colombo18arxiv): https://sites.google.com/view/bachprop
• 뮤직 트랜스포머(Transformer; huang19iclr): https://magenta.tensorflow.org/music-transformer

재배치(예: pop2piano)

• PiCoGen2(변압기, tan24ismir): https://tanchihpin0517.github.io/PiCoGen/
• PiCoGen(변압기, tan24icmr): https://tanchihpin0517.github.io/PiCoGen/
• Pop2Piano(변환기; choi23icassp): https://sweetcocoa.github.io/pop2piano_samples/
• audio2midi(GRU; wang21arxiv): https://github.com/ZZWaang/audio2midi
• InverseMV(GRU; lin21arxiv): https://github.com/linchintung/VMT

기존 음악을 결합하여 단일 트랙 다성 음악 작곡

• CollageNet(VAE; wuerkaixi21ismir): https://github.com/urkax/CollageNet

멀티트랙 음악 작곡

• Cadenza(변압기; lenz24ismir): https://lemo123.notion.site/Cadenza-A-Generative-Framework-for-Expressive-Ideas-Variations-7028ad6ac0ed41ac814b44928261cb68
• SymPAC(변압기, chen24ismir): 해당 없음
• MMT-BERT(변압기, zhu24ismir): 해당 없음
• 중첩된 음악 변환기(transformer; ryu24ismir): https://github.com/JudeJiwoo/nmt
• MMT-GI(변압기; xu23arxiv): https://goatlazy.github.io/MUSICAI/
• 모르페우스: https://dorienherremans.com/morpheus
• 예상 음악 변환기(; Thickstun23arxiv): https://crfm.stanford.edu/2023/06/16/anticipatory-music-transformer.html
• SCHmUBERT(확산; plasser23ijcai): https://github.com/plassma/symbolic-music-discrete-diffusion
• DiffuseRoll(확산; wang23arxiv): 해당 없음
• 뮤즈포머(Transformer; yu22neurips): https://ai-muzic.github.io/museformer/
• SymphonyNet(변압기, liu22ismir): https://symphonynet.github.io/
• CMT(변압기, di21mm): https://wzk1015.github.io/cmt/
• CONLON(GAN; angioloni20ismir): https://paolo-f.github.io/CONLON/
• MMM(변환기; ens20arxiv): https://jeffreyjohnens.github.io/MMM/
• 말러넷(RNN+VAE; lousseief19smc): https://github.com/fast-reflexes/MahlerNet
• 측정별 측정(RNN): https://sites.google.com/view/pjgbjzom
• JazzRNN(RNN; yeh19ismir-lbd): https://soundcloud.com/yating_ai/sets/ismir-2019-submission/
• MIDI-Sandwich2(RNN+VAE; liang19arxiv): https://github.com/LiangHsia/MIDI-S2
• LakhNES(변압기; donahue19ismir): https://chrisdonahue.com/LakhNES/
• MuseNet(트랜스포머): https://openai.com/blog/musenet/
• MIDI-VAE(GRU+VAE; brunner18ismir): https://www.youtube.com/channel/UCCkFzSvCae8ySmKCCWM5Mpg
• 멀티트랙 MusicVAE(LSTM+VAE; simon18ismir): https://magenta.tensorflow.org/multitrack
• MuseGAN(CNN+GAN; dong18aaai): https://salu133445.github.io/musegan/

멀티트랙 커버 작성(커버 생성, 참조 MIDI 필요)

• FigARO(변압기; rütte22arxiv): https://github.com/dvruette/figaro

주어진 코드, 멜로디를 작곡하다

• MelodyDiffusion(확산; li23mathematics): https://www.mdpi.com/article/10.3390/math11081915/s1
• H-EC2-VAE(GRU+VAE; wei21ismir): 해당 없음...
• MINGUS(변압기; madaghiele21ismir): https://github.com/vincenzomadaghiele/MINGUS
• 비밥넷(LSTM): https://shunithaviv.github.io/bebopnet/
• JazzGAN(GAN; trieu18mume): https://www.cs.hmc.edu/~keller/jazz/improvisor/
• XiaoIce 밴드(GRU; zhu18kdd): http://tv.cctv.com/2017/11/24/VIDEo7JWp0u0oWRmPbM4uCBt171124.shtml

주어진 멜로디, 코드 구성(멜로디 화음)

• ReaLchords(RL; wu24icml): https://storage.googleapis.com/realchords/index.html
• EMO-하모나이저(변압기): https://yuer867.github.io/emo_harmonizer/
• LHVAE(VAE+LSTM; ji23arxiv): 해당 없음
• DeepChoir(변압기; wu23icassp): https://github.com/sander-wood/deepchoir
• DAT-CVAE(transformer-vae; zhao22ismir): https://zhaojw1998.github.io/DAT_CVAE
• 서프라이즈넷(VAE; chen21ismir): https://github.com/scmvp301135/SurpriseNet
• MTHarmonizer(RNN; yeh21jnmr)

가사를 주고, 멜로디를 작곡하고

• CSL-L2M(LLM; wang25aaai): https://lichaiustc.github.io/CSL-L2M/
• MuDiT/MuSiT(LLM, wang24arxiv): 해당 없음
• SongComposer(LLM; ding24arxiv): https://pjlab-songcomposer.github.io/
• ROC(변압기; lv22arxiv): https://ai-muzic.github.io/roc/
• 팝멜로디(변압기, zhang22ismir): 해당 없음
• ReLyMe(변압기; chen22mm): https://ai-muzic.github.io/relyme/
• TeleMelody(변압기, ju21arxiv): https://github.com/microsoft/muzic
• 조건부 LSTM-GAN(LSTM+GAN; yu19arxiv): https://github.com/yy1lab/Lyrics-Conditioned-Neural-Melody-Generation
• iComposer(LSTM; lee19acl): https://www.youtube.com/watch?v=Gstzqls2f4A
• 작곡가(GRU; bao18arxiv): 해당 없음

드럼 MIDI 작곡

• Markis의 조건부 드럼 생성(BiLSTM/Transformer): https://github.com/melkor169/CP_Drums_Generation
• Nuttall의 모델(Transformer; nuttall21nime): https://nime.pubpub.org/pub/8947fhly/release/1?readingCollection=71dd0131
• Wei의 모델(VAE+GAN; wei19ismir): https://github.com/Sma1033/drum_ Generation_with_ssm
• DrumNet(GAE, lattner19waspaa): https://sites.google.com/view/drum- Generation
• DrumVAE(GRU+VAE; thio19milc): http://vibertthio.com/drum-vae-client

멜로디+코드 작곡(트랙 2개)

• 감성 리드 시트 생성(sen2seq): https://github.com/melkor169/LeadSheetGen_Valence
• EmoMusicTV(변압기; ji23tmm): https://github.com/Tayjsl97/EmoMusicTV
• 재즈 트랜스포머(Transformer; wu20ismir): https://drive.google.com/drive/folders/1-09SoxumYPdYetsUWHIHSugK99E2tNYD
• Transformer VAE(Transformer+VAE; jiang20icassp): https://drive.google.com/drive/folders/1Su-8qrK__28mAesSCJdjo6QZf9zEgIx6
• 2단계 RNN(RNN; deboom20arxiv): https://users.ugent.be/~cdboom/music/
• LeadsheetGAN(CRNN+GAN; liu18icmla): https://liuhaumin.github.io/LeadsheetArrangement/results
• LeadsheetVAE(RNN+VAE; liu18ismir-lbd): https://liuhaumin.github.io/LeadsheetArrangement/results

MIDI 트랙이 주어지면 다른 MIDI 트랙을 구성합니다.

• GETMusic(이산 확산): https://getmusicdemo.github.io/

멜로디나 리드시트를 주어 편곡을 구성

• AccoMontage3(;zhao23arxiv): https://zhaojw1998.github.io/AccoMontage-3
• GETMusic(이산 확산): https://getmusicdemo.github.io/
• SongDriver(변압기-CRF; wang22mm):
• AccoMontage2 : https://billyyi.top/accomontage2/
• AccoMontage(템플릿 기반, zhao21ismir): https://github.com/zhaojw1998/AccoMontage
• CP Transformer(변압기; hsiao21aaai): https://ailabs.tw/human-interaction/compound-word-transformer-generate-pop-piano-music-of-full-song-length/
• PopMAG(변압기, ren20mm): https://music-popmag.github.io/popmag/
• LeadsheetGAN: 위를 참조하세요
• LeadsheetVAE: 위 참조
• XiaoIce Band("다중 악기 공동 배열 모델"): 해당 없음

주어진 믹스(오디오), 베이스 작곡

• 잠재 확산(확산; pasini24arxiv): https://sonycslparis.github.io/bass_accompaniment_demo/
• BassNet(GAE+CNN; ren20mm): https://sonycslparis.github.io/bassnet/

프라임멜로디를 주어 멜로디+화음으로 작곡

• local_conv_music_세대(CNN; ouyang18arxiv): https://somedaywilldo.github.io/local_conv_music_ Generation/

프라임멜로디를 주어 멜로디+코드+베이스를 작곡합니다.

• BandNet(RNN; zhou18arxiv): https://soundcloud.com/yichao-zhou-555747812/sets/bandnet-sound-samples-1

주어진 피아노 악보를 보고 오케스트레이션을 작곡하다

• LOP(RBM; crestel17smc): https://qsdfo.github.io/LOP/results.html

피아노 충전

• 폴리퓨전(확산; min23ismir): https://polyffusion.github.io/
• 구조 인식 채우기 : https://tanchihpin0517.github.io/structure-aware_infilling
• VLI(변환기; chang21ismir): https://jackyhsiung.github.io/piano-infilling-demo/
• 피아노 인페인팅 애플리케이션(): https://ghadjeres.github.io/piano-inpainting-application/

멜로디 채우기

• CLSM(Transformer+LSTM; akama21ismir): https://contextual-latent-space-model.github.io/demo/

기호 영역 장르 스타일 이전

• Pop2Jazz(RNN; yeh19ismir-lbd): https://soundcloud.com/yating_ai/sets/ismir-2019-submission/
• Groove2Groove(RNN; cífka19ismir, cífka20taslp): https://groove2groove.telecom-paris.fr/
• CycleGAN2(CNN+GAN; brunner19mml): https://drive.google.com/drive/folders/1Jr_p6pnKvhA2YW9sp-ABChiFgV3gY1aT
• CycleGAN(CNN+GAN; brunner18ictai): https://github.com/sumuzhao/CycleGAN-Music-Style-Transfer
• FusionGAN(GAN; chen17icdm): http://people.cs.vt.edu/czq/publication/fusiongan/

기호 영역 배열 스타일 전송

• UnetED(CNN+Unet; hang19ijcai): https://biboamy.github.io/disentangle_demo/result/index.html

상징영역 감정/리듬/음조 스타일 전달

• MuseMorphose(Transformer+VAE; wu21arxiv): https://slseanwu.github.io/site-musemorphose/
• 카와이(VAE+GRU+adversarial; kawai20ismir): https://lisakawai.github.io/music_transformation/
• 왕(VAE+GRU; wang20ismir): https://github.com/ZZWaang/polyphonic-chord-texture-disentanglement
• 뮤직 페이더넷(VAE; tan20ismir): https://music-fadernets.github.io/
• 깊은 음악-유추(yang19ismir): https://github.com/cdyrhjohn/Deep-Music-Analogy-Demos

연주 생성(MIDI 제공, 인간과 유사한 MIDI 생성): 피아노만

• ScorePerformer(변환기, borovik23ismir): https://github.com/ilya16/scoreperformer
• CVRNN(CVRNN; maezawa19ismir): https://sites.google.com/view/cvrnn-performance-render
• GGNN (그래프 NN + 계층적 어텐션 RNN; jung19icml)
• VirtuosoNet(LSTM+계층적 주의 네트워크; jung18nipsw): https://www.youtube.com/playlist?list=PLkIVXCxCZ08rD1PXbrb0KNOSYVh5Pvg-c
• PerformanceRNN(RNN): https://magenta.tensorflow.org/performance-rnn

MIDI가 주어지면 인간과 유사한 MIDI 생성: 드럼만

• GrooVAE(seq2seq+VAE; gillick19icml): https://magenta.tensorflow.org/groovae

LLM으로 ABC MIDI 작성

• ComposerX(LLM; deng24arxiv): https://lllindsey0615.github.io/ComposerX_demo/