ȸ¿øµî·Ï £ü ºñ¹øºÐ½Ç
ȯ°æ,°æÁ¦,»ýÅÂ



4Â÷¿ø ½º¸¶Æ®½ÃƼ



ÇÁ·ÓÅ×Å©  

¤ýÀÛ¼ºÀÚ ½º¸¶Æ®¿ÀÅä½ÃƼ
¤ýÀÛ¼ºÀÏ 2016³â 11¿ù 26ÀÏ Åä¿äÀÏ
¤ýȨÆäÀÌÁö http://cpagent.com
¤ýLink#1 google-deepmind-ai-lip-reading-tv (Down:132)
¤ýÃßõ: 0  ¤ýÁ¶È¸: 3073      
±¸±ÛÀÇ ÀΰøÁö´ÉÆÀÀÎ 'µö¸¶Àεå(DeepMind)'¿Í '¿Á½ºÆ÷µå´ëÇÐ(Oxford)' ¿¬±¸ÁøÀÌ »ç¶÷ÀÇ ÀÔ¸ð¾çÀ» ºÐ¼®Çس»´Â ¼ÒÇÁÆ®¿þ¾î¸¦ °³¹ß

±¸±ÛÀÇ ÀΰøÁö´ÉÆÀÀÎ 'µö¸¶Àεå(DeepMind)'¿Í '¿Á½ºÆ÷µå´ëÇÐ(Oxford)' ¿¬±¸ÁøÀÌ »ç¶÷ÀÇ ÀÔ¸ð¾çÀ» ºÐ¼®Çس»´Â ¼ÒÇÁÆ®¿þ¾î¸¦ °³¹ßÇß´Ù°í ÇÕ´Ï´Ù




http://www.theverge.com/¡¦/13740798/google-deepmind-ai-lip-r¡¦





Google¡¯s AI can now lip read better than humans after watching thousands of hours of TV

The AI system annotated TV footage with 46.8 percent accuracy

Researchers from Google¡¯s AI division DeepMind and the University of Oxford have used artificial intelligence to create the most accurate lip-reading software ever. Using thousands of hours of TV footage from the BBC, scientists trained a neural network to annotate video footage with 46.8 percent accuracy. That might not seem that impressive at first — especially compared to AI accuracy rates when transcribing audio — but tested on the same footage, a professional human lip-reader was only able to get the right word 12.4 percent of the time.




The research follows similar work published by a separate group at the University of Oxford earlier this month. Using related techniques, these scientist were able to create a lip-reading program called LipNet that achieved 93.4 percent accuracy in tests, compared to 52.3 percent human accuracy. However, LipNet was only tested on specially-recorded footage that used volunteers speaking formulaic sentences. By comparison, DeepMind¡¯s software — known as ¡°Watch, Listen, Attend, and Spell¡± — was tested on far more challenging footage; transcribing natural, unscripted conversations from BBC politics shows.




More than 5,000 hours of footage from TV shows including NewsnightQuestion Time, and the World Today, was used to train DeepMind¡¯s ¡°Watch, Listen, Attend, and Spell¡± program. The videos included 118,000 difference sentences and some 17,500 unique words, compared to LipNet¡¯s test database of video of just 51 unique words.




DeepMind¡¯s researchers suggest that the program could have a host of applications, including helping hearing-impaired people understand conversations. It could also be used to annotate silent films, or allow you to control digital assistants like Siri or Alexa by just mouthing words to a camera (handy if you¡¯re using the program in public).




But when most people learn that an AI program has learned how to lip-read, their first thought is how it might be used for surveillance. Researchers say that there¡¯s still a big difference in transcribing brightly-lit, high resolution TV footage, and grainy CCTV video with a low frame rate, but you can¡¯t ignore the fact, that artificial intelligence seems to be closing this gap.




   
  0
3500
   
¹øÈ£     ±Û Á¦ ¸ñ  ÀÛ¼ºÀÚ ÀÛ¼ºÀÏ Á¶È¸
291 °í¸¿´Ù Æ÷Äϸó..ºÎÈ°ÇÑ AR, VR°ú ÇÔ²² '°ÔÀÓüÀÎÀú' µÉ±î [Æ÷Äϸó.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2016-07-15 3068
290 (½º¸¶Æ®¿ÀÅä½ÃƼ, ½º¸¶Æ®Ä«) »ï¼ºµµ ¶Ù¾îµç '½º¸¶Æ®Ä«' ½ÃÀå, Çö.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2015-12-14 3048
289 Çö½Çº¸´Ù ´õ Çö½Ç °°Àº... ¡°U¼¼»óÀÌ ¿­¸°´Ù 3dCTÆÀ 2009-10-17 3000
288 "¸ðµç °ÍÀº µ¥ÀÌÅÍ·Î ÅëÇÑ´Ù...ºòµ¥ÀÌÅÍ°¡ ½º¸¶Æ®½ÃƼ ¿ª·® Á¿ì.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2018-03-19 2937
287 ÀÎõ °Ë´Ü ½º¸¶Æ®½ÃƼ»ç¾÷ '»¡°£ºÒ'..¶¥°ª ÀÌ°ß ¸ø Á¼Çô ½º¸¶Æ®¿ÀÅä½ÃƼ 2015-12-19 2908
286 Åä°ø, ¿ëÀÎÈï´öÁö±¸¿¡ À¯½ÃƼ Á¶Çü¹° ¼³Ä¡ ceo 2008-02-29 2762
285 3Â÷¿ø ¸ðÇüÀº »õ·Î¿î Áöµµ¼­ºñ½º ¼öÀ͸𵨠3Â÷¿ø¸ðµ¨ÇϿ콺 2007-10-31 2757
284 [Áö¹æ¼Ò¸ê º¸°í¼­] ¨è ¼­¿ïº¸´Ù ³ÐÀº ±º(ÏÛ)¿¡ 1¸¸7õ¸íÀÌ »ê´Ù ½º¸¶Æ®µµ½ÃÀç»ý 2017-07-12 2734
283 ÀÎÅÚ ¸ðºô¾ÆÀÌ ¾Ï³í »þ½´¾Æ CEO, ¼¼°èÁö½ÄÆ÷·³¼­ °ø°³ Â÷°£ °Å¸®.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2017-10-19 2720
282 HDCÇö´ë»ê¾÷°³¹ß, ºÎµ¿»ê114 Àμö ¸¶¹«¸®..ÇÁ·ÓÅ×Å© ½Å±Ô»ç¾÷ Ãß.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2018-03-04 2640
281 Áß±¹, °æ±âºÎ¾çÃ¥ ºÒ±¸ 6³â ¹Ý¸¸¿¡ '6%' ¼ºÀå·ü·Î Ã߶ô moneyagent 2015-10-19 2617
280 Á¾ÇÕ ºÎµ¿»ê ±â¾÷ ¼±¾ðÇÑ Çö»ê, ºÎµ¿»ê114 Àû±Ø È°¿ë Á÷¹æ, ºÎµ¿.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2018-05-04 2609
279 ¸ð¹ÙÀÏ2.0½Ã´ë, ¡®ÄÜÅÙÃ÷¡¯°¡ Á¿ìÇÑ´Ù 3dCTÆÀ 2008-04-25 2542
278 ÀÌÅë»ç ÈÞ´ëÆùÁ¦Á¶ Çã¿ëÇϳª¡¦³í¶õ 3Â÷¿ø¼îÇθô 2008-02-29 2539
277 º¸±ÝÀÚ¸®ÁÖÅà ½Ã¹üÁö±¸ À§Ä¡µµ 3dCTÆÀ 2009-05-13 2518
276 [2017 °á»ê]'½º¸¶Æ®½ÃƼ' ´ëÇѹα¹ ¼ºÀ嵿·ÂÀ¸·Î ¹®ÀçÀÎ Á¤ºÎ 3°¡.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2017-12-26 2480
275 ³ì»ö¼ºÀå¹ý, ¹ÎÁÖ ÅðÀå¼Ó ƯÀ§Åë°ú ¿¡ÄÚ¸ÞÁö³×ÀÌ¼Ç 2009-11-09 2468
274 "½º¸¶Æ®½ÃƼ ÄÚ¸®¾Æ, ±Û·Î¹ú ±â¾÷ ¸ðÀÌ´Â ÇÖ Ç÷¹À̽º µÉ °Í" [ÇÏ.. smartcity 2015-12-28 2430
273 [ÀϹ®ÀÏ´ä]¿ÀÇ IPTV, ´ÙÀ½-MS-¼¿·± Àü·«Àº [1] 3Â÷¿ø¼îÇθô 2008-01-22 2377
272 ÆÄÁֽŵµ½Ã û¾à ÇÒ·Á¸é -»çÀ̹ö¸ðµ¨ÇϿ콺¸¦ °ü¶÷ÇÑ ÈÄ ÀÎÅͳÝû.. 3D¸ðµ¨ÇϿ콺 2007-11-05 2319
12345678910,,,20