Slide 11
Slide 11 text
-:$PSQPSBUJPO
ಈը۠ؒݕࡧͰԻڹใ༗ޮ׆༻͍ͨ͠
طଘͷಈը۠ؒݕࡧͰԻʹ·ͭΘΔΫΤϦ ྫɿݘͷ໐͖͕͢Δ۠ؒ
Λѻ͑ͳ͍
ΦʔσΟΦʹಛԽͨ͠Իڹ۠ؒݕࡧλεΫͷఏҊ <.VOBLBUB
*$"441`>
• ԻڹใͷΈʹணͨ͠σʔληοτͱϞσϧΛߏஙɼධՁ
• ࣮σʔλ͔ΒͳΔେنͳֶशɼධՁσʔληοτߏஙத ळࠒʹެ։༧ఆʂ
Իڹ۠ؒݕࡧ
Input long audio
Freq. [kHz]
0
16
8
0 10 20 30 50
40 60
Time [second]
Input text query Output moment
"Spectators are cheering and
shouting in a sports game"
44s
16s
[16s, 44s]
Audio moment retrieval