谷歌的新技术：一首歌能有多种风格（双语）

　　Facebook's AI Research (FAIR) division has created the neural network capable of hearing, for example, a jazz band play a song, and then is able to output that exact song in a completely different style of music, say, as if played by a punk rock band.

　　脸书的人工智能研究(简称FAIR)部门创造出具有听觉能力的神经网络，比如一首爵士乐队演奏的歌曲可以转化成一种完全不同的风格，像是朋克风格的演奏。

　　The result is nothing short of jaw-droppingly impressive–something even Facebook's AI researchers aren't shy of boasting about: Our results present abilities that are, as far as we know, unheard of.

　　转化的效果除了震惊还是震惊，连脸书人工智能的研究者也毫不保留地对此称道：我们展示的这项技术据我们所知应该是没有人听说过。

　　Asked to convert one musical instrument to another, our network is on par or slightly worse than professional musicians. Many times, people find it hard to tell which is the original audio file and which is the output of the conversion that mimics a completely different instrument.

　　谈到歌曲在不同乐器转换时，研究人员表示我们的这项技术和专业音乐人相比，旗鼓相当或稍逊色一点而已。人们很多次都听不出哪个是原版哪个是由完全不同乐器的翻奏。

　　You can listen to a series of original inputs (songs played by a real band) and the AI's outputs (the same song then translated into a different style) in the following video. Jump to the 4:14 mark to see a great example where an original MIDI of Elvis Presley's “Always On My Mind” is translated into a symphony piece as if it were played by Mozart.

　　你可以在下面的视频中听一系列的原声带(也就是由真人乐队演奏的歌曲)以及听通过AI技术输出的不同风格的音乐输出音频。跳到视频的4:14秒，你就能听到由埃尔维斯·普雷斯利演奏的《永远在我心中》的原声带被完美地翻奏成就好像是由莫扎特演奏的交响乐。