A list of demo websites for automatic music generation research

###interactive multi-track music composition

• Jamming with Yating (RNN; hsiao19ismir-lbd): https://www.youtube.com/watch?v=9ZIJrr6lmHg

###interactive piano composition

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

###interactive monoaural music composition

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

###compose melody

• meloform : 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): N/A...
• diffusion (diffusion+musicVAE; mittal21ismir): https://storage.googleapis.com/magentadata/papers/symbolic-music-diffusion/index.html
• MELONS (Transformer; zhou21arxiv): https://yiathena.github.io/MELONS/
• Sketchnet (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/

###compose single-track polyphonic music

• Compose & Embellish (Transformer; wu22arxiv): https://drive.google.com/drive/folders/1Y7HfExAz3PpPbFl0OnccxYDNF1KZUP-3
• Theme Transformer (Transformer; shih21arxiv): https://atosystem.github.io/ThemeTransformer/
• EMOPIA (Transformer; hung21ismir): https://annahung31.github.io/EMOPIA/
• dadagp (Transformer; sarmento21ismir): https://drive.google.com/drive/folders/1USNH8olG9uy6vodslM3iXInBT725zult
• CP Transformer (Transformer; 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
• Guitar Transformer (Transformer; chen20ismir): https://ss12f32v.github.io/Guitar-Transformer-Demo/
• Pop Music Transformer (Transformer; huang20mm): https://github.com/YatingMusic/remi
• Conditional Music Transformer (Transformer; choi19arxiv): https://storage.googleapis.com/magentadata/papers/music-transformer-autoencoder/index.html; and 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
• Amadeus (LSTM+RL; kumar19arxiv): https://goo.gl/ogVMSq
• Modularized VAE (GRU+VAE; wang19icassp): https://github.com/MiuLab/MVAE_Music
• BachProp (GRU; colombo18arxiv): https://sites.google.com/view/bachprop
• Music Transformer (Transformer; huang19iclr): https://magenta.tensorflow.org/music-transformer

###compose single-track polyphonic music by combinging existing ones

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

###compose multi-track music

• Museformer (Transformer; yu22neurips): https://ai-muzic.github.io/museformer/
• SymphonyNet (Transformer; liu22ismir): https://symphonynet.github.io/
• CMT (Transformer; di21mm): https://wzk1015.github.io/cmt/
• CONLON (GAN; angioloni20ismir): https://paolo-f.github.io/CONLON/
• MMM (Transformer; ens20arxiv): https://jeffreyjohnens.github.io/MMM/
• MahlerNet (RNN+VAE; lousseief19smc): https://github.com/fast-reflexes/MahlerNet
• measure-by-measure (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 (Transformer; donahue19ismir): https://chrisdonahue.com/LakhNES/
• MuseNet (Transformer): https://openai.com/blog/musenet/
• MIDI-VAE (GRU+VAE; brunner18ismir): https://www.youtube.com/channel/UCCkFzSvCae8ySmKCCWM5Mpg
• Multitrack MusicVAE (LSTM+VAE; simon18ismir): https://magenta.tensorflow.org/multitrack
• MuseGAN (CNN+GAN; dong18aaai): https://salu133445.github.io/musegan/

###compose multitrack music (cover generation; need reference MIDI)

• FIGARO (Transformer; rütte22arxiv): https://github.com/dvruette/figaro

###given chord, compose melody

• H-EC2-VAE (GRU+VAE; wei21ismir): N/A...
• MINGUS (Transformer; madaghiele21ismir): https://github.com/vincenzomadaghiele/MINGUS
• BebopNet (LSTM): https://shunithaviv.github.io/bebopnet/
• JazzGAN (GAN; trieu18mume): https://www.cs.hmc.edu/~keller/jazz/improvisor/
• XiaoIce Band (GRU; zhu18kdd): http://tv.cctv.com/2017/11/24/VIDEo7JWp0u0oWRmPbM4uCBt171124.shtml

###given melody, compose chord (harmonization)

• DAT-CVAE (transformer-vae; zhao22ismir): https://zhaojw1998.github.io/DAT_CVAE
• SurpriseNet (VAE; chen21ismir): https://github.com/scmvp301135/SurpriseNet
• MTHarmonizer (RNN; yeh21jnmr)

###given lyrics, compose melody

• ROC
• Conditional LSTM-GAN (LSTM+GAN; yu19arxiv): https://github.com/yy1lab/Lyrics-Conditioned-Neural-Melody-Generation
• iComposer (LSTM; lee19acl): https://www.youtube.com/watch?v=Gstzqls2f4A
• SongWriter (GRU; bao18arxiv): N/A

###compose drum MIDI

• Nuttall's model (Transformer; nuttall21nime): https://nime.pubpub.org/pub/8947fhly/release/1?readingCollection=71dd0131
• Wei's model (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

###compose melody+chords (two tracks)

• Jazz Transformer (Transformer; wu20ismir): https://drive.google.com/drive/folders/1-09SoxumYPdYetsUWHIHSugK99E2tNYD
• Transformer VAE (Transformer+VAE; jiang20icassp): https://drive.google.com/drive/folders/1Su-8qrK__28mAesSCJdjo6QZf9zEgIx6
• Two-stage 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

###given melody, compose arrangement

• SongDriver (Transformer-CRF; wang22mm):
• AccoMontage2 : https://billyyi.top/accomontage2/
• AccoMontage (template-based; zhao21ismir): https://github.com/zhaojw1998/AccoMontage
• CP Transformer (Transformer; hsiao21aaai): https://ailabs.tw/human-interaction/compound-word-transformer-generate-pop-piano-music-of-full-song-length/
• PopMAG (transformer; ren20mm): https://music-popmag.github.io/popmag/
• LeadsheetGAN: see above
• LeadsheetVAE: see above
• XiaoIce Band (the "multi-instrument co-arrangement model"): N/A

###given mix (audio), compose bass

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

###given prime melody, compose melody+chords

• local_conv_music_generation (CNN; ouyang18arxiv): https://somedaywilldo.github.io/local_conv_music_generation/

###given prime melody, compose melody+chords+bass

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

###given piano score, compose an orchestration

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

###piano infilling

• structure-aware infilling : https://tanchihpin0517.github.io/structure-aware_infilling
• VLI (Transformer; chang21ismir): https://jackyhsiung.github.io/piano-infilling-demo/
• The Piano Inpainting Application (): https://ghadjeres.github.io/piano-inpainting-application/

###melody infilling

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

###symbolic-domain genre style transfer

• 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/

###symbolic-domain arrangement style transfer

• UnetED (CNN+Unet; hung19ijcai): https://biboamy.github.io/disentangle_demo/result/index.html

###symbolic-domain emotion/rhythm/pitch style transfer

• MuseMorphose (Transformer+VAE; wu21arxiv): https://slseanwu.github.io/site-musemorphose/
• Kawai (VAE+GRU+adversarial; kawai20ismir): https://lisakawai.github.io/music_transformation/
• Wang (VAE+GRU; wang20ismir): https://github.com/ZZWaang/polyphonic-chord-texture-disentanglement
• Music FaderNets (VAE; tan20ismir): https://music-fadernets.github.io/
• deep-music-analogy (yang19ismir): https://github.com/cdyrhjohn/Deep-Music-Analogy-Demos

###given MIDI, generate human-like MIDI: Piano only

• CVRNN (CVRNN; maezawa19ismir): https://sites.google.com/view/cvrnn-performance-render
• GGNN (graph NN + hierarchical attention RNN; jeong19icml)
• VirtuosoNet (LSTM+hierarchical attention network; jeong18nipsw): https://www.youtube.com/playlist?list=PLkIVXCxCZ08rD1PXbrb0KNOSYVh5Pvg-c
• PerformanceRNN (RNN): https://magenta.tensorflow.org/performance-rnn

###given MIDI, generate human-like MIDI: Drum only

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

###given score, generate musical audio (performance): Piano only

• Wave2Midi2Wave (transformer+wavenet; hawthorne19iclr): https://magenta.tensorflow.org/maestro-wave2midi2wave

###given score, generate musical audio (performance): Not limited to Piano

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

###audio/timbre synthesis

• GANStrument (narita22arxiv): https://ganstrument.github.io/ganstrument-demo/
• NEWT (DDSP; hayes21ismir): https://benhayes.net/projects/nws/
• CRASH (diffusion; rouard21ismir): https://crash-diffusion.github.io/crash/
• DarkGAN (GAN; nistal21ismir): https://an-1673.github.io/DarkGAN.io/
• MP3net (GAN; broek21arxiv): https://korneelvdbroek.github.io/mp3net/
• Michelashvili (dsp-inspired; 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 (dsp-inspired; lamtharn20iclr): https://storage.googleapis.com/ddsp/index.html
• MelNet (auto-regressive; 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/
• SING (defossez18nips): https://research.fb.com/wp-content/themes/fb-research/research/sing-paper/
• WaveGAN (CNN+GAN; donahue19iclr): https://github.com/chrisdonahue/wavegan
• NSynth (WaveNet; engel17arxiv): https://magenta.tensorflow.org/nsynth

###audio-domain music generation

• musika! (GAN; pasini22ismir): https://huggingface.co/spaces/marcop/musika
• jukebox (VQVAE+Transformer; dhariwal20arxiv): https://openai.com/blog/jukebox/
• UNAGAN (GAN; liu20arxiv): https://github.com/ciaua/unagan
• dadabots (sampleRNN; carr18mume): http://dadabots.com/music.php

###text-to-music

• MusicLM (Transformer; agostinelli23arxiv): https://google-research.github.io/seanet/musiclm/examples/
• multi-source-diffusion-models (diffusion; 23arxiv): https://gladia-research-group.github.io/multi-source-diffusion-models/
• Noise2Music (diffusion; huang23arxiv): https://noise2music.github.io/
• ERNIE-Music (diffusion; zhu23arxiv): N/A
• riffusion (diffusion;): https://www.riffusion.com/
• Make-An-Audio (diffusion; huang23arxiv): https://text-to-audio.github.io/ (for general sounds)
• AudioLDM (diffusion; liu23arxiv): https://audioldm.github.io/ (for general sounds)
• AudioLM (Transformer; borsos22arxiv): https://google-research.github.io/seanet/audiolm/examples/ (for general sounds)

###given singing, generate accompaniments

• singsong (VQVAE+Transofmrer; donahue23arxiv): https://storage.googleapis.com/sing-song/index.html

###given drumless audio, generate drum accompaniments

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

###audio-domain singing synthesis

• NANSY++ (Transformer; choi23iclr): https://bald-lifeboat-9af.notion.site/Demo-Page-For-NANSY-67d92406f62b4630906282117c7f0c39
• 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/
• U-Singer (Transformer; kim22arxiv): https://u-singer.github.io/
• Singing-Tacotron (Transformer; wang22arxiv): https://hairuo55.github.io/SingingTacotron/
• KaraSinger (GRU/Transformer; liao22icassp): https://jerrygood0703.github.io/KaraSinger/
• VISinger (flow; zhang2): https://zhangyongmao.github.io/VISinger/
• MLP singer (mixer blocks; tae21arxiv): https://github.com/neosapience/mlp-singer
• LiteSing (wavenet; zhuang21icassp): https://auzxb.github.io/LiteSing/
• DiffSinger (diffusion; liu22aaai)[no duration modeling]: https://diffsinger.github.io/
• HiFiSinger (Transformer; chen20arxiv): https://speechresearch.github.io/hifisinger/
• DeepSinger (Transformer; ren20kdd): https://speechresearch.github.io/deepsinger/
• xiaoice-multi-singer: https://jiewu-demo.github.io/INTERSPEECH2020/
• xiaoicesing: https://xiaoicesing.github.io/
• bytesing: https://bytesings.github.io/
• mellotron: https://nv-adlr.github.io/Mellotron
• lee's model (lee19arxiv): http://ksinging.mystrikingly.com/
• http://home.ustc.edu.cn/~yiyh/interspeech2019/

###audio-domain singing style transfer

• 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/
• polyak20interspeech (GAN; polyak20interspeech): https://singing-conversion.github.io/
• speech2sing2 (GAN; wu20interspeech): https://ericwudayi.github.io/Speech2Singing-DEMO/
• speech2sing (encoder/decoder; parekh20icassp): https://jayneelparekh.github.io/icassp20/
• SINGAN (GAN; sisman19apsipa): N/A
• [MSVC-GAN] (GAN): https://hujinsen.github.io/
• https://mtg.github.io/singing-synthesis-demos/voice-cloning/
• https://enk100.github.io/Unsupervised_Singing_Voice_Conversion/
• Yong&Nam (DSP; yong18icassp): https://seyong92.github.io/singing-expression-transfer/
• cybegan (CNN+GAN; wu18faim): http://mirlab.org/users/haley.wu/cybegan/

###audio-domain singing correction

• deep-autotuner (CGRU; wagner19icassp): http://homes.sice.indiana.edu/scwager/deepautotuner.html

###audio-domain style transfer (general)

• 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

• VITS (transformer+flow+GAN; kim21icml): https://github.com/jaywalnut310/vits

###vocoder

• sawsing (DDSP; wu22ismir): https://ddspvocoder.github.io/ismir-demo/
• Multi-Singer (wavenet; huang21mm): https://multi-singer.github.io/
• SingGAN (GAN; chen21arxiv): https://singgan.github.io/
• DiffWave (diffusion; kong21iclr): https://diffwave-demo.github.io/
• MelGAN (GAN; kumar19neurips): https://melgan-neurips.github.io/

###audio-domain loop generation

• pjloopgan (GAN; yeh22ismir): https://arthurddd.github.io/PjLoopGAN/
• loopgen (GAN; hung21ismir): https://loopgen.github.io/