| [ | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_073.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which clip sounds more 'up close' and in back? The clips are separated by 0.5 seconds. Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_094.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which clip sounds like it's facing you directly? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_013.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "An audio sequence contains two segments with a brief pause. Which one is perceived as originating from the front direction? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_024.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Judge which clip has a more frontal spatial image. The two are joined by 0.5 seconds of silence. Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_088.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which one sounds like it's in front, not reflected or reverberant? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_097.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which clip sounds like it's in back, not part of the reverb tail? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_043.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which segment sounds like it's projecting from the front? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_025.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which sound appears to be in back, not encoded for rear speakers? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_082.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which sound is more perceptually dominant in the front direction? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_011.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "In terms of depth perception, which clip is more forward? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_061.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which of the two clips is more clearly perceived as frontal? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_046.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which clip sounds more immediate and forward? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_059.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which clip is perceived as being in front rather than in the back? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_075.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which clip appears to be in front, even if quiet? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_026.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which one gives the impression of being in front, even in mono? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_049.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which one gives the impression of being directly in front? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_093.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which one sounds like it's spatially closer and more forward? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_042.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which of the two clips sounds like it's in back, not panned to the back? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_054.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which of the two clips sounds like it's in the back, not the rear? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_055.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which one sounds like it's in the foreground? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_015.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Determine which of the two sounds is more forward-facing. Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_062.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which segment is more prominent in the back auditory field? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_053.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which of the two clips gives a stronger impression of being in front? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_069.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which of the two clips feels like it's coming from the front speaker? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_034.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which of the two clips sounds less distant and more frontal? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_086.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Determine which segment sounds like it's positioned ahead. The clips have a 0.5-second silent gap. Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_078.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Evaluate which clip is more likely to be coming from the front. There is 0.5 seconds of silence between them. Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_030.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "You are given a concatenated audio of two clips with 0.5 seconds of silence in between. Which one sounds like it's coming from the front? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_014.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which of the two clips is more perceptually forward? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_070.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which of the two clips sounds like it's in front, not from the periphery? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_091.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Listen to two clips separated by 0.5 seconds of silence. Which one appears to be more forward in space? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_058.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which one sounds like it's in front, not simulated for surround? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_031.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which one feels like it's in back, not behind the head? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_018.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which of the two sounds appears to be closer to the listener? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_048.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which clip seems to be in front, based on its perceived distance? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_021.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which sound appears to be coming from the front, not the back? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_017.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which clip sounds like it's in front, not delayed or shadowed? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_096.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which clip feels like it's in back, not delayed or recessed? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_008.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which sound seems to be in back, based on interaural cues? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_032.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which clip seems to be in front, not muffled or recessed? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_004.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which clip is more likely to be interpreted as frontal in a 3D audio context? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_006.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which sound appears to be in front, even if subtle? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_068.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which of the two clips sounds more 'present' and frontal? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_074.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which one sounds like it's not in the background but in front? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_081.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which one appears to be in front, based on early reflections? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_095.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which of the two clips feels like it's in back, not spatially decorrelated? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_051.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which sound appears to be in back, not filtered or equalized for rear? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_000.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which clip is more likely to be labeled as 'back' in a listening test? Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "B" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_098.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Assess which clip is perceptually closer in the front. There is 0.5 seconds of silence between them. Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| }, | |
| { | |
| "voice": [ | |
| "direction/task_comparison/direction_pair_065.wav" | |
| ], | |
| "conversations": [ | |
| { | |
| "from": "human", | |
| "value": "Which one sounds like it's ahead rather than behind? The audio has two clips with a short gap. Only answer letter 'A' (refers to the first clip) or 'B' (refers to the second clip). Do not add any explanation, punctuation, or extra text. <audio>" | |
| }, | |
| { | |
| "from": "gpt", | |
| "value": "A" | |
| } | |
| ] | |
| } | |
| ] |