GAN　has　recently　been　proved　to　be　able　to　generate　symbolic　music　in　the　form　of　piano-rolls.　However,　those　existing　GAN-based　multi-track　music　generation　methods　are　always　unstable.　Moreover,　due　to　defects　in　the　temporal　features　extraction,　the　generated　multi-track　music　does　not　sound　natural　enough.　Therefore,　we　propose　a　new　GAN　model　with　self-attention　mechanism,　DMB-GAN,　which　can　extract　more　temporal　features　of　music　to　generate　multi-instruments　music　stably.　First　of　all,　to　generate　more　consistent　and　natural　single-track　music,　we　introduce　self-attention　mechanism　to　enable　GAN-based　music　generation　model　to　extract　not　only　spatial　features　but　also　temporal　features.　Secondly,　to　generate　multi-instruments　music　with　harmonic　structure　among　all　tracks,　we　construct　a　dual　generative　adversarial　architecture　with　multi-branches,　each　branch　for　one　track.　Finally,　to　improve　generated　quality　of　multi-instruments　symbolic　music,　we　introduce　switchable　normalization　to　stabilize　network　training.　The　experimental　results　show　that　DMB-GAN　can　stably　generate　coherent,　natural　multi-instruments　music　with　good　quality.　©　2019　IEEE.