dots.tts.edit-demo / data /samples.json
whk-sjtu's picture
chore: refresh curated demo assets
468639e verified
Raw
History Blame Contribute Delete
55.7 kB
{
"schema_version": 1,
"title": "dots.tts.edit",
"catalog_fingerprint": "746b255476160936117a35a21dc2ded1b803bb26bf6046e16ed87c98281eb8ff",
"selection_sha256": "ac2de6a310092df70ba262743459ca7e2f837db1ab263d793f5a3746e88da5d5",
"sample_count": 29,
"audio_count": 136,
"sections": [
{
"benchmark": "text",
"title": "Text Editing",
"samples": [
{
"candidate_id": "text:easy-0727:text_edit__easy-0727__0727_en_0032",
"canonical_id": "text_edit__easy-0727__0727_en_0032",
"language": "en",
"focus": "Two localized substitutions while preserving the speaker's distinctive pronunciation and surrounding prosody.",
"tags": [
"en",
"2 ops",
"bulk_sub"
],
"instruction_html": "<div class=\"edit-canvas\">&quot;How I <span class=\"operation-span operation-text\"><span class=\"operation-source\">wish</span><span class=\"operation-label\">Replace with “long”</span></span> you could <span class=\"operation-span operation-text\"><span class=\"operation-source\">get</span><span class=\"operation-label\">Replace with “obtain”</span></span> me a copy of that picture, Philip,&quot; Laura said, entreatingly.</div>",
"source_audio": "demos/text/text_edit__easy-0727__0727_en_0032/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/text/text_edit__easy-0727__0727_en_0032/ours_45k.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/text/text_edit__easy-0727__0727_en_0032/qwen3_omni.wav"
},
{
"system_id": "mimo_audio_instruct",
"label": "MiMo Audio Instruct",
"kind": "baseline",
"audio": "demos/text/text_edit__easy-0727__0727_en_0032/mimo_audio_instruct.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/text/text_edit__easy-0727__0727_en_0032/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "text:easy-0727:text_edit__easy-0727__0727_en_0057",
"canonical_id": "text_edit__easy-0727__0727_en_0057",
"language": "en",
"focus": "A single long-span edit at the end of an extended English utterance.",
"tags": [
"en",
"1 ops",
"sub",
"long_source"
],
"instruction_html": "<div class=\"edit-canvas\">The exigencies of the modern industrial system frequently place individuals and households in juxtaposition between whom there is little contact in any other sense than that of juxtaposition. One&#x27;s neighbors, mechanically speaking, often are socially not one&#x27;s neighbors, or even acquaintances; and still their <span class=\"operation-span operation-text\"><span class=\"operation-source\">transient good opinion has a high degree of utility</span><span class=\"operation-label\">Replace with “brief approval remains highly useful”</span></span>.</div>",
"source_audio": "demos/text/text_edit__easy-0727__0727_en_0057/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/text/text_edit__easy-0727__0727_en_0057/ours_45k.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/text/text_edit__easy-0727__0727_en_0057/qwen3_omni.wav"
},
{
"system_id": "mimo_audio_instruct",
"label": "MiMo Audio Instruct",
"kind": "baseline",
"audio": "demos/text/text_edit__easy-0727__0727_en_0057/mimo_audio_instruct.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/text/text_edit__easy-0727__0727_en_0057/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "text:easy-0727:text_edit__easy-0727__0727_zh_0052",
"canonical_id": "text_edit__easy-0727__0727_zh_0052",
"language": "zh",
"focus": "Mandarin substitution plus insertion, with the original mouse click and pauses left intact.",
"tags": [
"zh",
"2 ops",
"mixed",
"insert_present",
"expansion"
],
"instruction_html": "<div class=\"edit-canvas\">本届亚运会上没有获得<span class=\"operation-span operation-text\"><span class=\"operation-source\">任何奖牌</span><span class=\"operation-label\">Replace with “金牌”</span></span>。<span class=\"operation-point operation-text\">Insert “但多名选手进入了决赛。”</span></div>",
"source_audio": "demos/text/text_edit__easy-0727__0727_zh_0052/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/text/text_edit__easy-0727__0727_zh_0052/ours_45k.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/text/text_edit__easy-0727__0727_zh_0052/qwen3_omni.wav"
},
{
"system_id": "mimo_audio_instruct",
"label": "MiMo Audio Instruct",
"kind": "baseline",
"audio": "demos/text/text_edit__easy-0727__0727_zh_0052/mimo_audio_instruct.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/text/text_edit__easy-0727__0727_zh_0052/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "text:easy-0727:text_edit__easy-0727__0727_zh_0075",
"canonical_id": "text_edit__easy-0727__0727_zh_0075",
"language": "zh",
"focus": "A localized substitution inside a long Mandarin list.",
"tags": [
"zh",
"1 ops",
"bulk_sub"
],
"instruction_html": "<div class=\"edit-canvas\">其他提名包括最佳影片、最佳导演、最佳摄影、最佳服装设计、最佳电影剪辑、最佳原创配乐、最佳艺术指导、最佳音效剪辑、最佳混音和<span class=\"operation-span operation-text\"><span class=\"operation-source\">最佳原创剧本</span><span class=\"operation-label\">Replace with “最佳改编剧本”</span></span>。</div>",
"source_audio": "demos/text/text_edit__easy-0727__0727_zh_0075/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/text/text_edit__easy-0727__0727_zh_0075/ours_45k.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/text/text_edit__easy-0727__0727_zh_0075/qwen3_omni.wav"
},
{
"system_id": "mimo_audio_instruct",
"label": "MiMo Audio Instruct",
"kind": "baseline",
"audio": "demos/text/text_edit__easy-0727__0727_zh_0075/mimo_audio_instruct.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/text/text_edit__easy-0727__0727_zh_0075/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "text:hard-0727:text_edit__hard-0727__hard_0727_en_0107",
"canonical_id": "text_edit__hard-0727__hard_0727_en_0107",
"language": "en",
"focus": "Three operations rewrite nearly the entire sentence while retaining the source speaker style.",
"tags": [
"en",
"3 ops",
"mixed",
"acronym_or_allcaps",
"multiop_ge3",
"delete_present"
],
"instruction_html": "<div class=\"edit-canvas\"><span class=\"operation-span operation-text\"><span class=\"operation-source\">For, it must be stated to those who are ignorant of the case</span><span class=\"operation-label\">Replace with “NASA ”</span></span><span class=\"operation-point operation-text\">Insert “changed”</span><span class=\"operation-span operation-text operation-delete\"><span class=\"operation-source\">, that argot is both a literary phenomenon and a social result</span><span class=\"operation-label\">Delete</span></span>.</div>",
"source_audio": "demos/text/text_edit__hard-0727__hard_0727_en_0107/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/text/text_edit__hard-0727__hard_0727_en_0107/ours_45k.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/text/text_edit__hard-0727__hard_0727_en_0107/qwen3_omni.wav"
},
{
"system_id": "mimo_audio_instruct",
"label": "MiMo Audio Instruct",
"kind": "baseline",
"audio": "demos/text/text_edit__hard-0727__hard_0727_en_0107/mimo_audio_instruct.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/text/text_edit__hard-0727__hard_0727_en_0107/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "text:hard-0727:text_edit__hard-0727__hard_0727_zh_0208",
"canonical_id": "text_edit__hard-0727__hard_0727_zh_0208",
"language": "zh",
"focus": "Two long-span Mandarin substitutions compress the source into a short target.",
"tags": [
"zh",
"2 ops",
"mixed",
"chinese_numerals",
"compression"
],
"instruction_html": "<div class=\"edit-canvas\"><span class=\"operation-span operation-text\"><span class=\"operation-source\">摄政王广场由摄政王大街呈东西向贯通</span><span class=\"operation-label\">Replace with “结果”</span></span><span class=\"operation-span operation-text\"><span class=\"operation-source\">,另有南北六条较小的街道与广场相通</span><span class=\"operation-label\">Replace with “变了”</span></span>。</div>",
"source_audio": "demos/text/text_edit__hard-0727__hard_0727_zh_0208/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/text/text_edit__hard-0727__hard_0727_zh_0208/ours_45k.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/text/text_edit__hard-0727__hard_0727_zh_0208/qwen3_omni.wav"
},
{
"system_id": "mimo_audio_instruct",
"label": "MiMo Audio Instruct",
"kind": "baseline",
"audio": "demos/text/text_edit__hard-0727__hard_0727_zh_0208/mimo_audio_instruct.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/text/text_edit__hard-0727__hard_0727_zh_0208/expert_data_pipeline.wav"
}
]
}
]
},
{
"benchmark": "emotion",
"title": "Emotion Editing",
"samples": [
{
"candidate_id": "emotion:curated-312:emotion_edit__curated-312__emo_c312_043_phrase",
"canonical_id": "emotion_edit__curated-312__emo_c312_043_phrase",
"language": "en",
"focus": "Localized anger on one English phrase while the surrounding context remains neutral.",
"tags": [
"en",
"single_phrase",
"angry"
],
"instruction_html": "<div class=\"edit-canvas\">When God made these different races he knew that the superior would enslave the inferior, knew that <span class=\"operation-span operation-emotion\"><span class=\"operation-source\">the inferior would be conquered</span><span class=\"operation-label\">Emotion · Angry · level 2</span></span>, and finally destroyed.</div>",
"source_audio": "demos/emotion/emotion_edit__curated-312__emo_c312_043_phrase/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_043_phrase/ours_45k.wav"
},
{
"system_id": "step_audio_editx",
"label": "Step-Audio-EditX",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_043_phrase/step_audio_editx.wav"
},
{
"system_id": "ming_uniaudio",
"label": "Ming-UniAudio",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_043_phrase/ming_uniaudio.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_043_phrase/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "emotion:curated-312:emotion_edit__curated-312__emo_c312_012_phrase",
"canonical_id": "emotion_edit__curated-312__emo_c312_012_phrase",
"language": "en",
"focus": "A natural phrase-level sadness edit aligned with the sentence semantics.",
"tags": [
"en",
"single_phrase",
"sad"
],
"instruction_html": "<div class=\"edit-canvas\">&quot;Mary, your father and I are going out to ride this afternoon, and <span class=\"operation-span operation-emotion\"><span class=\"operation-source\">I am sorry, for your sake</span><span class=\"operation-label\">Emotion · Sad · level 2</span></span>, that we can not take you with us.&quot;</div>",
"source_audio": "demos/emotion/emotion_edit__curated-312__emo_c312_012_phrase/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_012_phrase/ours_45k.wav"
},
{
"system_id": "step_audio_editx",
"label": "Step-Audio-EditX",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_012_phrase/step_audio_editx.wav"
},
{
"system_id": "ming_uniaudio",
"label": "Ming-UniAudio",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_012_phrase/ming_uniaudio.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_012_phrase/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "emotion:curated-312:emotion_edit__curated-312__emo_c312_057_phrase",
"canonical_id": "emotion_edit__curated-312__emo_c312_057_phrase",
"language": "zh",
"focus": "Localized low-arousal sadness in Mandarin.",
"tags": [
"zh",
"single_phrase",
"sad"
],
"instruction_html": "<div class=\"edit-canvas\">然而列宁因为<span class=\"operation-span operation-emotion\"><span class=\"operation-source\">他的妹妹奥利加因伤寒逝世</span><span class=\"operation-label\">Emotion · Sad · level 2</span></span>而未能出席毕业典礼。</div>",
"source_audio": "demos/emotion/emotion_edit__curated-312__emo_c312_057_phrase/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_057_phrase/ours_45k.wav"
},
{
"system_id": "step_audio_editx",
"label": "Step-Audio-EditX",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_057_phrase/step_audio_editx.wav"
},
{
"system_id": "ming_uniaudio",
"label": "Ming-UniAudio",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_057_phrase/ming_uniaudio.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_057_phrase/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "emotion:curated-312:emotion_edit__curated-312__emo_c312_080_multi",
"canonical_id": "emotion_edit__curated-312__emo_c312_080_multi",
"language": "zh",
"focus": "Two Mandarin spans receive different emotions: anger and fear.",
"tags": [
"zh",
"multi_span",
"angry+afraid"
],
"instruction_html": "<div class=\"edit-canvas\">还包括<span class=\"operation-span operation-emotion\"><span class=\"operation-source\">禁毒行动和处理</span><span class=\"operation-label\">Emotion · Angry · level 2</span></span>大规模毁灭性武器的<span class=\"operation-span operation-emotion\"><span class=\"operation-source\">恐怖活动所造成</span><span class=\"operation-label\">Emotion · Afraid · level 2</span></span>的后果。</div>",
"source_audio": "demos/emotion/emotion_edit__curated-312__emo_c312_080_multi/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_080_multi/ours_45k.wav"
},
{
"system_id": "step_audio_editx",
"label": "Step-Audio-EditX",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_080_multi/step_audio_editx.wav"
},
{
"system_id": "ming_uniaudio",
"label": "Ming-UniAudio",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_080_multi/ming_uniaudio.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_080_multi/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "emotion:curated-312:emotion_edit__curated-312__emo_c312_010_whole",
"canonical_id": "emotion_edit__curated-312__emo_c312_010_whole",
"language": "en",
"focus": "Whole-sentence melancholic rendering for contrast with localized emotion edits.",
"tags": [
"en",
"whole_sentence",
"melancholic"
],
"instruction_html": "<div class=\"edit-canvas\"><span class=\"operation-span operation-emotion\"><span class=\"operation-source\">To be or not to be, that is the question; whether &#x27;tis nobler in the mind to suffer the slings and arrows-What? No, Hamlet speaking.</span><span class=\"operation-label\">Emotion · Melancholic · level 2</span></span></div>",
"source_audio": "demos/emotion/emotion_edit__curated-312__emo_c312_010_whole/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_010_whole/ours_45k.wav"
},
{
"system_id": "step_audio_editx",
"label": "Step-Audio-EditX",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_010_whole/step_audio_editx.wav"
},
{
"system_id": "ming_uniaudio",
"label": "Ming-UniAudio",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_010_whole/ming_uniaudio.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/emotion/emotion_edit__curated-312__emo_c312_010_whole/expert_data_pipeline.wav"
}
]
}
]
},
{
"benchmark": "prosody",
"title": "Prosody Editing",
"samples": [
{
"candidate_id": "prosody:medium:prosody_edit__medium__en_input_0054_wave_2",
"canonical_id": "prosody_edit__medium__en_input_0054_wave_2",
"language": "en",
"focus": "Three English regions combine slower rate, higher pitch, and faster rate.",
"tags": [
"en",
"mixed",
"clause",
"3 regions"
],
"instruction_html": "<div class=\"edit-canvas\">But, <span class=\"operation-span operation-rate\"><span class=\"operation-source\">in spite of my blindness,</span><span class=\"operation-label\">Rate · 0.81×</span></span> <span class=\"operation-span operation-pitch\"><span class=\"operation-source\">I will be caught</span><span class=\"operation-label\">Pitch · +4 semitones</span></span> neither in her net <span class=\"operation-span operation-rate\"><span class=\"operation-source\">nor in the Queen&#x27;s.</span><span class=\"operation-label\">Rate · 1.2×</span></span></div>",
"source_audio": "demos/prosody/prosody_edit__medium__en_input_0054_wave_2/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/prosody/prosody_edit__medium__en_input_0054_wave_2/ours_45k.wav"
},
{
"system_id": "ming_uniaudio",
"label": "Ming-UniAudio",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__en_input_0054_wave_2/ming_uniaudio.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__en_input_0054_wave_2/qwen3_omni.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__en_input_0054_wave_2/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "prosody:medium:prosody_edit__medium__en_input_0038_wave_2",
"canonical_id": "prosody_edit__medium__en_input_0038_wave_2",
"language": "en",
"focus": "Three pitch regions move in different directions within one sentence.",
"tags": [
"en",
"pitch",
"clause",
"3 regions"
],
"instruction_html": "<div class=\"edit-canvas\">As our boat <span class=\"operation-span operation-pitch\"><span class=\"operation-source\">flashed down the rollers</span><span class=\"operation-label\">Pitch · +5 semitones</span></span> <span class=\"operation-span operation-pitch\"><span class=\"operation-source\">into the water</span><span class=\"operation-label\">Pitch · -4 semitones</span></span> <span class=\"operation-span operation-pitch\"><span class=\"operation-source\">I made this song</span><span class=\"operation-label\">Pitch · +3 semitones</span></span> and sang it:</div>",
"source_audio": "demos/prosody/prosody_edit__medium__en_input_0038_wave_2/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/prosody/prosody_edit__medium__en_input_0038_wave_2/ours_45k.wav"
},
{
"system_id": "ming_uniaudio",
"label": "Ming-UniAudio",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__en_input_0038_wave_2/ming_uniaudio.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__en_input_0038_wave_2/qwen3_omni.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__en_input_0038_wave_2/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "prosody:medium:prosody_edit__medium__zh_input_0035_wave_3",
"canonical_id": "prosody_edit__medium__zh_input_0035_wave_3",
"language": "zh",
"focus": "Two Mandarin pitch regions shift emphasis to different words.",
"tags": [
"zh",
"pitch",
"clause",
"2 regions"
],
"instruction_html": "<div class=\"edit-canvas\">于是我决定<span class=\"operation-span operation-pitch\"><span class=\"operation-source\">就来谈谈</span><span class=\"operation-label\">Pitch · -5 semitones</span></span><span class=\"operation-span operation-pitch\"><span class=\"operation-source\">种族问题</span><span class=\"operation-label\">Pitch · +9 semitones</span></span></div>",
"source_audio": "demos/prosody/prosody_edit__medium__zh_input_0035_wave_3/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/prosody/prosody_edit__medium__zh_input_0035_wave_3/ours_45k.wav"
},
{
"system_id": "ming_uniaudio",
"label": "Ming-UniAudio",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__zh_input_0035_wave_3/ming_uniaudio.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__zh_input_0035_wave_3/qwen3_omni.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__zh_input_0035_wave_3/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "prosody:medium:prosody_edit__medium__en_input_0019_wave_2",
"canonical_id": "prosody_edit__medium__en_input_0019_wave_2",
"language": "en",
"focus": "A single region controls the speaking rate of an entire long English sentence.",
"tags": [
"en",
"rate",
"sentence",
"1 regions"
],
"instruction_html": "<div class=\"edit-canvas\"><span class=\"operation-span operation-rate\"><span class=\"operation-source\">This service Plautus rendered, consciously or unconsciously, by making two Carthaginian soldiers talk Phoenician; that service Moliere rendered, by making so many of his characters talk Levantine and all sorts of dialects.</span><span class=\"operation-label\">Rate · 0.88×</span></span></div>",
"source_audio": "demos/prosody/prosody_edit__medium__en_input_0019_wave_2/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/prosody/prosody_edit__medium__en_input_0019_wave_2/ours_45k.wav"
},
{
"system_id": "ming_uniaudio",
"label": "Ming-UniAudio",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__en_input_0019_wave_2/ming_uniaudio.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__en_input_0019_wave_2/qwen3_omni.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__en_input_0019_wave_2/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "prosody:medium:prosody_edit__medium__zh_input_0019_wave_3",
"canonical_id": "prosody_edit__medium__zh_input_0019_wave_3",
"language": "zh",
"focus": "Whole-utterance rate control over a Mandarin digit sequence.",
"tags": [
"zh",
"rate",
"sentence",
"1 regions"
],
"instruction_html": "<div class=\"edit-canvas\"><span class=\"operation-span operation-rate\"><span class=\"operation-source\">九四零七五一幺九七三九</span><span class=\"operation-label\">Rate · 1.19×</span></span></div>",
"source_audio": "demos/prosody/prosody_edit__medium__zh_input_0019_wave_3/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/prosody/prosody_edit__medium__zh_input_0019_wave_3/ours_45k.wav"
},
{
"system_id": "ming_uniaudio",
"label": "Ming-UniAudio",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__zh_input_0019_wave_3/ming_uniaudio.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__zh_input_0019_wave_3/qwen3_omni.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/prosody/prosody_edit__medium__zh_input_0019_wave_3/expert_data_pipeline.wav"
}
]
}
]
},
{
"benchmark": "pause",
"title": "Pause Editing",
"samples": [
{
"candidate_id": "pause:full-0727:pause_edit_benchmark__full-0727__pe_0001",
"canonical_id": "pause_edit_benchmark__full-0727__pe_0001",
"language": "en",
"focus": "Insert one long pause at a natural English boundary.",
"tags": [
"en",
"ins",
"1 edits",
"levels=3"
],
"instruction_html": "<div class=\"edit-canvas\">He threw it down at the approach of mrs Luna, laughed, <span class=\"operation-point operation-pause\">Insert pause · level 3</span>shook hands with her, and said in answer to her last remark, &quot;You imply that you do tell fibs.</div>",
"source_audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0001/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0001/ours_45k.wav"
},
{
"system_id": "mimo_audio_instruct",
"label": "MiMo Audio Instruct",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0001/mimo_audio_instruct.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0001/qwen3_omni.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0001/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "pause:full-0727:pause_edit_benchmark__full-0727__pe_0158",
"canonical_id": "pause_edit_benchmark__full-0727__pe_0158",
"language": "zh",
"focus": "Insert one long pause at a Mandarin phrase boundary.",
"tags": [
"zh",
"ins",
"1 edits",
"levels=3"
],
"instruction_html": "<div class=\"edit-canvas\">但是非常考虑到整体的一个<span class=\"operation-point operation-pause\">Insert pause · level 3</span>家用的</div>",
"source_audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0158/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0158/ours_45k.wav"
},
{
"system_id": "mimo_audio_instruct",
"label": "MiMo Audio Instruct",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0158/mimo_audio_instruct.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0158/qwen3_omni.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0158/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "pause:full-0727:pause_edit_benchmark__full-0727__pe_0190",
"canonical_id": "pause_edit_benchmark__full-0727__pe_0190",
"language": "zh",
"focus": "Insert two short pauses within one Mandarin utterance.",
"tags": [
"zh",
"ins",
"2 edits",
"levels=1,1"
],
"instruction_html": "<div class=\"edit-canvas\">让<span class=\"operation-point operation-pause\">Insert pause · level 1</span>消费者得以全面地了解和体验李宁<span class=\"operation-point operation-pause\">Insert pause · level 1</span>专业运动产品</div>",
"source_audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0190/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0190/ours_45k.wav"
},
{
"system_id": "mimo_audio_instruct",
"label": "MiMo Audio Instruct",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0190/mimo_audio_instruct.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0190/qwen3_omni.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0190/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "pause:full-0727:pause_edit_benchmark__full-0727__pe_0083",
"canonical_id": "pause_edit_benchmark__full-0727__pe_0083",
"language": "en",
"focus": "Reduce one existing pause in English.",
"tags": [
"en",
"red",
"1 edits",
"levels=2"
],
"instruction_html": "<div class=\"edit-canvas\">I shouldn&#x27;t wonder- <span class=\"operation-point operation-pause\">Reduce pause · level 2</span>But they&#x27;ve probably spoiled her, so that she&#x27;d be tiresome if one met her again.&quot;</div>",
"source_audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0083/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0083/ours_45k.wav"
},
{
"system_id": "mimo_audio_instruct",
"label": "MiMo Audio Instruct",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0083/mimo_audio_instruct.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0083/qwen3_omni.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0083/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "pause:full-0727:pause_edit_benchmark__full-0727__pe_0135",
"canonical_id": "pause_edit_benchmark__full-0727__pe_0135",
"language": "en",
"focus": "Reduce three English pauses with fine-grained timing control.",
"tags": [
"en",
"red",
"3 edits",
"levels=1,1,1"
],
"instruction_html": "<div class=\"edit-canvas\">These rapscallions wanted to try the Nonesuch again, <span class=\"operation-point operation-pause\">Reduce pause · level 1</span>because there was so much money in it, <span class=\"operation-point operation-pause\">Reduce pause · level 1</span>but they judged it wouldn&#x27;t be safe, <span class=\"operation-point operation-pause\">Reduce pause · level 1</span>because maybe the news might a worked along down by this time.</div>",
"source_audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0135/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0135/ours_45k.wav"
},
{
"system_id": "mimo_audio_instruct",
"label": "MiMo Audio Instruct",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0135/mimo_audio_instruct.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0135/qwen3_omni.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/pause/pause_edit_benchmark__full-0727__pe_0135/expert_data_pipeline.wav"
}
]
}
]
},
{
"benchmark": "multi",
"title": "Compositional Editing",
"samples": [
{
"candidate_id": "multi:balanced-240:multi_edit__balanced-240__multi_edit_balanced-240_me_0050",
"canonical_id": "multi_edit__balanced-240__multi_edit_balanced-240_me_0050",
"language": "en",
"focus": "Combine English pause reduction with localized rate control.",
"tags": [
"en",
"prosody+pause",
"2 components"
],
"instruction_html": "<div class=\"edit-canvas\">But, <span class=\"operation-point operation-pause\">Reduce pause · level 2</span>I thank God, an imagination took him one morning that <span class=\"operation-span operation-rate\"><span class=\"operation-source\">he was falling into a dropsy</span><span class=\"operation-label\">Rate · 1.25×</span></span>, and made him in such haste to go back to Cambridge to his doctor, that he never remembers anything he has to ask of me, but the coach to carry him away.</div>",
"source_audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0050/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0050/ours_45k.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0050/qwen3_omni.wav"
},
{
"system_id": "step_audio_editx",
"label": "Step-Audio-EditX",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0050/step_audio_editx.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0050/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "multi:balanced-240:multi_edit__balanced-240__multi_edit_balanced-240_me_0004",
"canonical_id": "multi_edit__balanced-240__multi_edit_balanced-240_me_0004",
"language": "en",
"focus": "Combine an English pause edit with localized melancholic emotion.",
"tags": [
"en",
"emotion+pause",
"2 components"
],
"instruction_html": "<div class=\"edit-canvas\">So great was the cry of the wounded, that the prior of the abbey with all his monks came forth, <span class=\"operation-point operation-pause\">Reduce pause · level 2</span>who, when they <span class=\"operation-span operation-emotion\"><span class=\"operation-source\">saw these poor wretches so slain amongst the vines</span><span class=\"operation-label\">Emotion · Melancholic · level 2</span></span>, and wounded to death, confessed some of them.</div>",
"source_audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0004/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0004/ours_45k.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0004/qwen3_omni.wav"
},
{
"system_id": "step_audio_editx",
"label": "Step-Audio-EditX",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0004/step_audio_editx.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0004/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "multi:balanced-240:multi_edit__balanced-240__multi_edit_balanced-240_me_0165",
"canonical_id": "multi_edit__balanced-240__multi_edit_balanced-240_me_0165",
"language": "zh",
"focus": "Combine Mandarin pitch control with pause insertion.",
"tags": [
"zh",
"prosody+pause",
"2 components"
],
"instruction_html": "<div class=\"edit-canvas\">让市民自行选择<span class=\"operation-span operation-pitch\"><span class=\"operation-source\">非制订排列</span><span class=\"operation-label\">Pitch · -4 semitones</span></span>英文字母<span class=\"operation-point operation-pause\">Insert pause · level 2</span>及阿拉伯数字作为车辆登记号码。</div>",
"source_audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0165/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0165/ours_45k.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0165/qwen3_omni.wav"
},
{
"system_id": "step_audio_editx",
"label": "Step-Audio-EditX",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0165/step_audio_editx.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0165/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "multi:balanced-240:multi_edit__balanced-240__multi_edit_balanced-240_me_0214",
"canonical_id": "multi_edit__balanced-240__multi_edit_balanced-240_me_0214",
"language": "zh",
"focus": "Combine Mandarin text substitution with pause insertion.",
"tags": [
"zh",
"text+pause",
"2 components"
],
"instruction_html": "<div class=\"edit-canvas\">法团<span class=\"operation-point operation-pause\">Insert pause · level 2</span>亦同时<span class=\"operation-span operation-text\"><span class=\"operation-source\">向时任特首的梁振英</span><span class=\"operation-label\">Replace with “向相关部门”</span></span>及城市大学动物医学院的捐助者求助。</div>",
"source_audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0214/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0214/ours_45k.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0214/qwen3_omni.wav"
},
{
"system_id": "step_audio_editx",
"label": "Step-Audio-EditX",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0214/step_audio_editx.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0214/expert_data_pipeline.wav"
}
]
},
{
"candidate_id": "multi:balanced-240:multi_edit__balanced-240__multi_edit_balanced-240_me_0198",
"canonical_id": "multi_edit__balanced-240__multi_edit_balanced-240_me_0198",
"language": "zh",
"focus": "Three-way Mandarin edit combining text, emotion, and speaking rate.",
"tags": [
"zh",
"text+emotion+prosody",
"3 components"
],
"instruction_html": "<div class=\"edit-canvas\">就在墨线上<span class=\"operation-span operation-rate\"><span class=\"operation-source\">拴上一根银针插在脚下</span><span class=\"operation-label\">Rate · 0.8×</span></span>在变换方位后<span class=\"operation-span operation-emotion\"><span class=\"operation-source\">继续牵引墨线</span><span class=\"operation-label\">Emotion · Calm · level 2</span></span>一共走了九九八十一步<span class=\"operation-span operation-text\"><span class=\"operation-source\">九根银针</span><span class=\"operation-label\">Replace with “三枚铜钱”</span></span>被我以品字形全部插好</div>",
"source_audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0198/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Our model · 45k",
"kind": "ours",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0198/ours_45k.wav"
},
{
"system_id": "qwen3_omni",
"label": "Qwen3-Omni",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0198/qwen3_omni.wav"
},
{
"system_id": "step_audio_editx",
"label": "Step-Audio-EditX",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0198/step_audio_editx.wav"
},
{
"system_id": "expert_data_pipeline",
"label": "Expert Data Pipeline",
"kind": "baseline",
"audio": "demos/multi/multi_edit__balanced-240__multi_edit_balanced-240_me_0198/expert_data_pipeline.wav"
}
]
}
]
},
{
"benchmark": "noise",
"title": "Noise Preservation & Denoising",
"samples": [
{
"candidate_id": "200638dd80c84bf1ac1c26cb873cb1c4",
"canonical_id": "200638dd80c84bf1ac1c26cb873cb1c4",
"language": "en",
"focus": "Text editing while preserving continuous background noise.",
"tags": [
"English",
"Noise preservation"
],
"instruction_html": "<div class=\"edit-canvas\">&quot;How I <span class=\"operation-span operation-text\"><span class=\"operation-source\">wish</span><span class=\"operation-label\">Replace with “hope”</span></span> you could get me a copy of that picture, Philip,&quot; Laura said, entreatingly.</div>",
"source_audio": "demos/noise/200638dd80c84bf1ac1c26cb873cb1c4/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Ours · 45k",
"kind": "ours",
"audio": "demos/noise/200638dd80c84bf1ac1c26cb873cb1c4/ours_45k.wav"
}
]
},
{
"candidate_id": "9f20ec35b544411aab21db298ee5b6d0",
"canonical_id": "9f20ec35b544411aab21db298ee5b6d0",
"language": "zh",
"focus": "Denoising while preserving the original content and speaker identity.",
"tags": [
"Mandarin",
"Denoising"
],
"instruction_html": "<div class=\"edit-canvas\"><span class=\"operation-span operation-text\"><span class=\"operation-source\">本届亚运会上没有获得任何奖牌。</span><span class=\"operation-label\">Enhance</span></span></div>",
"source_audio": "demos/noise/9f20ec35b544411aab21db298ee5b6d0/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Ours · 45k",
"kind": "ours",
"audio": "demos/noise/9f20ec35b544411aab21db298ee5b6d0/ours_45k.wav"
}
]
}
]
},
{
"benchmark": "multi_speaker",
"title": "Multi-speaker Preservation",
"samples": [
{
"candidate_id": "e26db2858abb400f9e8ab261fcf565e9",
"canonical_id": "e26db2858abb400f9e8ab261fcf565e9",
"language": "zh",
"focus": "Editing one speaker while preserving the second speaker.",
"tags": [
"Mandarin",
"Two speakers"
],
"instruction_html": "<div class=\"edit-canvas\">好像看见了一个<span class=\"operation-span operation-text\"><span class=\"operation-source\">红头发</span><span class=\"operation-label\">Replace with “蓝头发”</span></span>的家伙。 上次你说鞋子有点磨脚,我给你买了一双软软的鞋垫,这样你垫上之后应该会舒服很多。</div>",
"source_audio": "demos/multi_speaker/e26db2858abb400f9e8ab261fcf565e9/source.wav",
"systems": [
{
"system_id": "ours_45k",
"label": "Ours · 45k",
"kind": "ours",
"audio": "demos/multi_speaker/e26db2858abb400f9e8ab261fcf565e9/ours_45k.wav"
}
]
}
]
}
]
}