å¤ãã®äººãéããã¼ãã£ã¼ä¼å ´ã®ãããªãããããã®äººãè«ç¬ãã¦ããä¸ã§ãèªåã®ååãèå³ã®ãã話ãèªç¶ã¨èãåããã¨ãã§ããç¾è±¡ã¯ãã«ã¯ãã«ãã¼ãã£ã¼å¹æãã¨å¼ã°ãã人éãæã¤è½åãé¸æç注æãã®ä»£è¡¨ä¾ã¨ããã¦ãã¾ããGoogleã®ç 究è ã¯ããã£ã¼ãã©ã¼ãã³ã°ãç¨ãããã¨ã§ã³ã³ãã¥ã¼ã¿ã¼ã«èªåã§æ··ããåã£ãé³å£°ãåé¢ããæè¡ãç¿å¾ããã¦ãã³ã³ãã¥ã¼ã¿ã¼ã«ã«ã¯ãã«ãã¼ãã£ã¼å¹æã身ã«ä»ãããããã¨ã«æåãã¾ããã [1804.03619] Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation https://arxiv.org/abs/1804.03619 Research Blog: Looking to Listen: Audio-Vis
{{#tags}}- {{label}}
{{/tags}}