首页> 外文会议>European Conference on Artificial Intelligence >Towards a Complete Classical Music Companion
【24h】

Towards a Complete Classical Music Companion

机译:走向完整的古典音乐伴侣

获取原文

摘要

We present a system that listens to music on-line and almost instantly identifies the piece the performers are playing and the exact position in the musical score. This is achieved via a combination of a state-of-the-art audio-to-note transcription algorithm and a novel symbolic fingerprinting method. The speed and precision of the system are evaluated in systematic experiments with a large corpus of classical music recordings. The results indicate extremely fast and accurate recognition performance - a level of performance, in fact, that even human experts in classical music will find hard to match.
机译:我们提出了一个在线听音乐的系统,几乎立即识别表演者正在播放的作品以及音乐分数中的确切位置。这是通过最先进的音频到记录转录算法和新颖的符号指纹方法的组合来实现的。系统的速度和精度在系统实验中评估了具有大型古典音乐录制的大语料库。结果表明了极快和准确的识别性能 - 事实上,即使是古典音乐的人类专家也会难以匹配。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号