# All Hail The Mighty Translatotron! ## Метаданные - **Канал:** Two Minute Papers - **YouTube:** https://www.youtube.com/watch?v=38ZXwJj6j8k - **Дата:** 20.06.2019 - **Длительность:** 5:57 - **Просмотры:** 96,071 ## Описание ❤️ Pick up cool perks on our Patreon page: https://www.patreon.com/TwoMinutePapers My talk and the full panel discussion at the NATO conference (I start at around the 12:30 minute mark): ▶️ https://www.facebook.com/StratComCOE/videos/698737203889068/ 📝 The paper "Direct speech-to-speech translation with a sequence-to-sequence model" and the voice samples are available here: https://arxiv.org/abs/1904.06037 https://google-research.github.io/lingvo-lab/translatotron/#conversational 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: 313V, Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Brian Gilman, Bruno Brito, Bryan Learn, Christian Ahlin, Christoph Jadanowski, Claudio Fernandes, Daniel Hasegan, Dennis Abts, Eric Haddad, Eric Martel, Evan Breznyik, Geronimo Moralez, Ivelin Ivanov, James Watt, Javier Bustamante, John De Witt, Kaiesh Vohra, Kasia Hayden, Kjartan Olason, Levente Szabo, Lorin Atzberger, Marcin Dukaczewski, Marten Rauschenberg, Maurits van Mastrigt, Michael Albrecht, Michael Jensen, Nader Shakerin, Owen Campbell-Moore, Owen Skarpness, Raul Araújo da Silva, Richard Reis, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Zach Boldyga. https://www.patreon.com/TwoMinutePapers Splash screen/thumbnail design: Felícia Fehér - http://felicia.hu Károly Zsolnai-Fehér's links: Facebook: https://www.facebook.com/TwoMinutePapers/ Twitter: https://twitter.com/karoly_zsolnai Web: https://cg.tuwien.ac.at/~zsolnai/ #Translatotron ## Содержание ### [0:00](https://www.youtube.com/watch?v=38ZXwJj6j8k) Segment 1 (00:00 - 05:00) dear fellow scholars this is two minute papers with károly Shana if I hear scientists at Google just released the translator Tron this is an AI that is able to translate speech from one language into speech into another language and here comes the first twist without using text as an intermediate representation you give it the sound waves and you get the translated sound waves and this neural network was trained approximately on a million voice samples so let's see what learning on this one million samples gives us listen this is the input sentence in Spanish II I'm a no school state P de and here it is translated to English but using the voice of the same person and you will not know unless you ask they have their say-so stop doing that nuevos empleados de cranfield university new hires at Cranfield University this is incredible however there is another twist perhaps an even bigger one believe it or not this technique can not only translate but also perform voice transfer so it can say the same thing using someone else's voice this means that the AI not only has to learn what to say but how to say it this is immensely difficult it's also not easy to know what we need to listen to and when so let me walk you through it this is a sentence in Spanish non Archon Delphinus this is the same sentence said by someone else an actual person and in English swimming with dolphins and now the same thing but synthesized by the algorithm using both of their voices swimming with dolphins let's listen to them side-by-side some more swimming with dolphins this is so good let's have a look at some more examples por lo tanto madad alrededor del país you look a mess so look around the country and what do you see you see Wow the method performs the learning by trying to map these mouths spectrograms between multiple speakers you can see example sentences here and there corresponding spectrograms which are concise representations of someone's voice and intonation and of course it is difficult to mathematically formalise what makes a good translation and a good mimicking of someone's voice so in these cases we'll let people be the judge and have them listen to a few speech signals and asking them to guess which was the real person and which was the AI speaking if you take a closer look at the paper you will see that it smokes the competition this is great progress on an immensely difficult task as we have to perform proper translation and voice transfer at the same time it's quite a challenge of course failure cases still exist listen then she is a la cosa dan yeah that's the thing down damn yeah that's just imagine that you are in a foreign country and all you need to do is use your phone to test stories to people not only in their own language but also using your own voice even if you don't speak a word of their language beautiful even this video could perhaps be available in a variety of languages using my own voice within the next few years although I wonder how these algorithms would pronounce my name so far that proved to be quite a challenge for humans and a eyes are like and for now all hail the mighty translator Tron in the mean time I just got back from this year's NATO conference it was an incredible honor to get an invitation to speak at such an event and of course I was happy to attend as a service to the public the goal of the talk was to inform key ### [5:00](https://www.youtube.com/watch?v=38ZXwJj6j8k&t=300s) Segment 2 (05:00 - 05:00) political and military decision-makers about recent developments in AI so they can make better decisions for us and I was so nervous during the talk my goodness if you wish to watch it I put a link to it in the video description and I may be able to upload a higher quality version of this video here in the future attending the conference introduced delays in our schedule my apologies for that and normally we would have to worry whether because of this we'll have enough income to improve our recording equipment however with your support on patreon this is not at all the case so I want to send you a big thank you for all your amazing support this was really all possible thanks to you if you wish to support us just go to patreon. com/scishow to scripture have fun with the video thanks for watching and for your generous support and I'll see you next time --- *Источник: https://ekstraktznaniy.ru/video/14297*