词条 | Adobe Voco |
释义 |
Adobe Voco is an audio editing and generating prototype software by Adobe that enables novel editing and generation of audio. It has been dubbed "Photoshop-for-voice".[1] It was first previewed at the Adobe MAX event in November 2016. The technology shown at Adobe MAX was a preview that could potentially be incorporated into Adobe Creative Cloud Technical detailsAs the demo showed, the software takes approximately 20 minutes of the desired target's speech and then generated sound-alike voice with even phonemes that were not present in the target example material. Adobe has stated Voco will lower the cost of audio production.[1] With the introduction of Adobe Voco and the similarly capable WaveNet, produced by DeepMind.[1] ConcernsEthical and security concerns have been raised over the ability to alter an audio recording to include words and phrases the original speaker never spoke, and the potential risk to voiceprint biometrics.[2] There are also concerns that it may be used in conjunction with:
AlternativesAdobe's lack of publicized progress has opened opportunities for other companies to build alternative products to VOCO, such as LyreBird[5]. References1. ^{{cite web |url= https://deepmind.com/blog/wavenet-generative-model-raw-audio/ |title= WaveNet: A Generative Model for Raw Audio |last= |first= |date= 2016-09-08 |website= Deepmind.com |publisher= |access-date= 2017-05-24 |quote= }} {{Simulation-software-stub}}2. ^1 2 {{cite web |url= https://www.bbc.com/news/technology-37899902 |title= Adobe Voco 'Photoshop-for-voice' causes concern |last= |first= |date= 2016-11-07 |website= BBC.com |publisher= BBC |access-date= 2016-07-05 |quote= }} 3. ^{{cite web |last1=Rodgers |first1=Julian |title=Adobe Voco - Should We Be Afraid? |url=https://www.pro-tools-expert.com/home-page/2016/11/16/adobe-voco-should-we-be-afraid |website=Production Expert |publisher=Pro Tools |accessdate=14 December 2018}} 4. ^{{cite web | last = Thies | first = Justus | author-link = | title = Face2Face: Real-time Face Capture and Reenactment of RGB Videos | work = | publisher = Proc. Computer Vision and Pattern Recognition (CVPR), IEEE | year = 2016 | url = http://www.graphics.stanford.edu/~niessner/thies2016face.html | doi = | accessdate = 2016-06-18}} 5. ^{{Cite web|url=https://lyrebird.ai/|title=Lyrebird - Create a digital copy of voice|website=lyrebird.ai|language=en|access-date=2018-03-27}} 1 : Speech synthesis |
随便看 |
|
开放百科全书收录14589846条英语、德语、日语等多语种百科知识,基本涵盖了大多数领域的百科知识,是一部内容自由、开放的电子版国际百科全书。