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¸: 3075      
±¸±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¸
371 ÀÎÅÚ ¸ðºô¾ÆÀÌ ¾Ï³í »þ½´¾Æ CEO, ¼¼°èÁö½ÄÆ÷·³¼­ °ø°³ Â÷°£ °Å¸®.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2017-10-19 2721
370 [4Â÷ »ê¾÷Çõ¸í À§¿øȸ Ãâ¹ü]À¯¿µ¹Î °ú±âÁ¤ÅëºÎ Àå°ü "´ëÇѹα¹ 4.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2017-10-11 1401
369 ¿ÃÇØ µµ½ÃÀç»ý ´ºµô ½Ã¹ü »ç¾÷Áö 70°÷¸¸ ¼±Á¤..40°÷ Ãà¼Ò 1) ÃÊ´Ü.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2017-09-14 1735
368 ¿ì¹ö¡¤¸®ÇÁÆ® ÀÚÀ²ÁÖÇàÂ÷ ´Þ¸®´Âµ¥ ½îÄ«¡¤±×¸°Ä« "ÀÚÀ²ÁÖÇà °èȹ.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2017-08-14 1833
367 ÀÎÅÚÀÌ 17Á¶¿¡ »ê ÀÚÀ²ÁÖÇà ±â¼ú.. À̽º¶ó¿¤¿£ ÀÌ·± ÀÚÀ²ÁÖÇà º¥.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2017-07-29 2103
366 [½º¸¶Æ®½ÃƼ AI¿£Áø] AI½Ã´ë, °³Àο¡°Ô Áß¿äÇÑ °Ç 'Á÷¾÷' ¾Æ´Ñ '.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2017-07-27 1895
365 [Áö¹æ¼Ò¸ê º¸°í¼­] ¨ê "¿ì¸° ÀÌ·¸°Ô ±Øº¹Çß¾î¿ä"..ÀÏÀÚ¸®°¡ ºñ°á.. ½º¸¶Æ®µµ½ÃÀç»ý 2017-07-12 3632
364 [Áö¹æ¼Ò¸ê º¸°í¼­] ¨é Ãâ»êÀå·Á±Ý 1õ¸¸¿ø¿¡µµ Àα¸´Â µÇ·¹ °¨¼Ò.. ½º¸¶Æ®µµ½ÃÀç»ý 2017-07-12 2116
363 [Áö¹æ¼Ò¸ê º¸°í¼­] ¨è ¼­¿ïº¸´Ù ³ÐÀº ±º(ÏÛ)¿¡ 1¸¸7õ¸íÀÌ »ê´Ù ½º¸¶Æ®µµ½ÃÀç»ý 2017-07-12 2735
362 [Áö¹æ¼Ò¸ê º¸°í¼­] ¨ç "30³â ³» 84°³ ½Ã±º »ç¶óÁ®"..Àα¸°¨¼Ò °ø.. [1] ½º¸¶Æ®µµ½ÃÀç»ý 2017-07-12 4720
361 SKÅÚ·¹ÄÞ, ÀÚÀÛ¿ë VR Á¦ÀÛ Ç÷§Æû 'T real VR Studio' °ø°³ ±â»ç.. 3DARSNS 2017-05-18 8971
360 OPenCV + AI + ÄÄÇ»ÅͺñÀü :e·¯´×¡¤eÅ×½ºÆà ºÐ¾ß¿¡¼­ÀÇ ¾ó±¼ÀÎÁõ.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2017-03-06 1701
359 [½º¸¶Æ®½ÃƼ] U-City °Ç¼³¹ý ¡æ ¡¸½º¸¶Æ®µµ½Ã Á¶¼º ¹× »ê¾÷ÁøÈï¹ý.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2017-03-03 3706
358 [½º¸¶Æ®±³Åë] ÀΰøÁö´ÉÀÇ ÁøÈ­ µû¶ó..Á¡Á¡ ´õ ¶È¶ÈÇØÁö´Â ÀÚÀ²ÁÖ.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2017-02-15 2256
357 [½º¸¶Æ®½ÃƼ, ½º¸¶Æ®±³Åë] ¹Ì¸® °¡º» °¡±î¿î ¹Ì·¡..'À¶ÇÕ¡¤Çõ½ÅÀÇ.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2017-01-09 1965
356 (½½·Î¿ì´º½º) ¹Ì±¹ ÀΰøÁö´É º¸°í¼­ÀÇ ÁÖ¿ä ³»¿ë ½º¸¶Æ®¿ÀÅä½ÃƼ 2016-12-28 1729
355 [½º¸¶Æ®±³Åë]ÀÏ, Ä¡¸Å ¿îÀüÀÚ ±³Åë»ç°í·Î '°ñÄ¡' ½º¸¶Æ®¿ÀÅä½ÃƼ 2016-12-16 2005
354 ±Û·Î¹ú IT ±â¾÷µéÀÇ ¾ÕÀ¸·Î ¼º°ú¸¦ ÆÇ°¡¸§ ÇÏ´Â ´ëÂ÷´ëÁ¶Ç¥¿¡ Ŭ.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2016-11-29 2152
353 ±¸±ÛÀÇ ÀΰøÁö´ÉÆÀÀÎ 'µö¸¶Àεå(DeepMind)'¿Í '¿Á½ºÆ÷µå´ëÇÐ(Oxf.. ½º¸¶Æ®¿ÀÅä½ÃƼ 2016-11-26 3075
352 SKT¡¤BMW, ¼¼°è ÃÖÃÊ 5G Ä¿³ØƼµåÄ« ½Ã¿¬ ½º¸¶Æ®¿ÀÅä½ÃƼ 2016-11-15 3238
12345678910,,,20