ChristophSchuhmann's picture
Add EmoNet Voice Bench results (42/42 classes, pooled r=0.304 rho=0.323) + eval artifacts
c75e48d verified
Raw
History Blame Contribute Delete
9.28 kB
{
"dataset": "t1a5anu-anon/emonet-voice-bench",
"revision": "c0067f7b2c1b303d77394b42c09836f7be84932c",
"license": "cc-by-4.0",
"gated": false,
"private": false,
"downloaded_to": "/e/data1/datasets/playground/mmlaion/schuhmann1/dramabox/headspub/bench/emonet/data",
"download_complete": true,
"total_bytes": 1077182855,
"paper": "arXiv:2506.09827 - EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection",
"splits": {
"train": {
"n_rows": 12600,
"note": "ONLY split in repo; it IS the eval/benchmark set despite being named 'train'"
}
},
"configs": [
"default"
],
"files": [
{
"path": "data/data/train-00000-of-00003.parquet",
"bytes": 366186448,
"num_rows": 4200
},
{
"path": "data/data/train-00001-of-00003.parquet",
"bytes": 354533930,
"num_rows": 4200
},
{
"path": "data/data/train-00002-of-00003.parquet",
"bytes": 356462477,
"num_rows": 4200
}
],
"schema": {
"audioId": "struct<bytes: binary, path: string> (HF Audio feature; MP3 bytes embedded in parquet)",
"label": "string holding a Python-repr list of per-annotator dicts, e.g. \"[{'human-1': {'Shame': 1}}, {'human-2': {'Shame': 2}}]\"; emotion names are URL-encoded (%20, %26)"
},
"audio": {
"encoding": "MP3 (MPEG Layer III), ID3v2 tagged",
"storage": "embedded in parquet as bytes; NOT extracted to loose files",
"sample_rate_hz": 44100,
"channels": 1,
"duration_sec": {
"min": 0.20800453514739228,
"max": 224.35,
"mean": 10.235554517150774,
"median": 6.348990929705216,
"total_hours": 35.82444081002771
}
},
"label_space": {
"n_classes": 42,
"classes": [
"Affection",
"Amusement",
"Anger",
"Arousal",
"Astonishment",
"Authenticity",
"Awe",
"Bitterness",
"Concentration",
"Confusion",
"Contemplation",
"Contempt",
"Contentment",
"Disappointment",
"Disgust",
"Distress",
"Doubt",
"Elation",
"Embarrassment",
"Emotional Numbness",
"Fatigue",
"Fear",
"Helplessness",
"Hope",
"Impatience and Irritability",
"Infatuation",
"Interest",
"Intoxication",
"Jealousy & Envy",
"Longing",
"Malevolence",
"Pain",
"Pleasure",
"Pride",
"Relief",
"Sadness",
"Sexual Lust",
"Shame",
"Sourness",
"Teasing",
"Thankfulness",
"Triumph"
],
"task": "per-(clip, target-emotion) INTENSITY rating. Exactly ONE target emotion per row, rated 0/1/2 by 2-4 experts. NOT multi-label, NOT a 42-way argmax task.",
"intensity_scale": {
"0": "Not Present",
"1": "Mildly Present",
"2": "Intensely Present"
},
"official_gold_mapping": "0->0, 1->5, 2->10 on a 0-10 scale; averaged across annotators (column gold_0_10)",
"n_annotators_per_clip": {
"2": 4538,
"3": 7719,
"4": 343
},
"annotator_ids": [
"human-1",
"human-2",
"human-3",
"human-4",
"human-5",
"human-6"
],
"rows_per_class": {
"Affection": 300,
"Amusement": 300,
"Anger": 300,
"Arousal": 300,
"Astonishment": 300,
"Authenticity": 300,
"Awe": 300,
"Bitterness": 300,
"Concentration": 300,
"Confusion": 300,
"Contemplation": 300,
"Contempt": 300,
"Contentment": 300,
"Disappointment": 300,
"Disgust": 300,
"Distress": 300,
"Doubt": 300,
"Elation": 300,
"Embarrassment": 300,
"Emotional Numbness": 300,
"Fatigue": 300,
"Fear": 300,
"Helplessness": 300,
"Hope": 300,
"Impatience and Irritability": 300,
"Infatuation": 300,
"Interest": 300,
"Intoxication": 300,
"Jealousy & Envy": 300,
"Longing": 300,
"Malevolence": 300,
"Pain": 300,
"Pleasure": 300,
"Pride": 300,
"Relief": 300,
"Sadness": 300,
"Sexual Lust": 300,
"Shame": 300,
"Sourness": 300,
"Teasing": 300,
"Thankfulness": 300,
"Triumph": 300
},
"mean_intensity_per_class": {
"Shame": 1.1183,
"Helplessness": 1.0269,
"Astonishment": 1.0606,
"Bitterness": 1.2369,
"Concentration": 1.4022,
"Contentment": 1.0994,
"Disgust": 1.0589,
"Confusion": 1.1197,
"Affection": 1.1239,
"Infatuation": 1.2125,
"Thankfulness": 1.0492,
"Triumph": 1.1783,
"Pride": 1.0856,
"Longing": 0.9539,
"Sadness": 0.8925,
"Anger": 1.2011,
"Jealousy & Envy": 1.1639,
"Arousal": 0.7769,
"Intoxication": 0.92,
"Contempt": 1.1728,
"Impatience and Irritability": 1.1036,
"Emotional Numbness": 0.6581,
"Distress": 1.1619,
"Teasing": 0.9997,
"Pleasure": 0.9189,
"Sourness": 1.1617,
"Authenticity": 1.0475,
"Disappointment": 1.175,
"Fatigue": 0.9125,
"Interest": 1.0983,
"Doubt": 1.02,
"Elation": 0.9908,
"Sexual Lust": 0.8378,
"Fear": 0.9011,
"Malevolence": 1.1603,
"Amusement": 1.0042,
"Contemplation": 1.1425,
"Embarrassment": 1.1661,
"Awe": 0.8586,
"Pain": 1.0086,
"Hope": 0.9064,
"Relief": 1.0814
},
"annotation_counts_by_intensity": {
"0": 10828,
"1": 9009,
"2": 13768
}
},
"unique_audio_files": 12397,
"duplicate_audio_note": "197 mp3 filenames each appear in 2 rows, always with a DIFFERENT target emotion -> the unit of evaluation is (audio_path,label); clip_id is unique per row",
"consensus_subsets": {
"unanimous_rows": 2912,
"present_all_annotators": 4692,
"present_any_annotator": 11475,
"absent_all": 1125
},
"official_metric": {
"primary": [
"MAE",
"RMSE",
"Pearson r",
"Spearman rho"
],
"evidence": "arXiv:2506.09827 (https://arxiv.org/html/2506.09827v1), evaluation section / Table 5: 'our primary evaluation employs metrics suited for regression and correlation analysis on a common scale. The 3-level intensity human judgments (0: Not Present, 1: Mildly Present, 2: Intensely Present) are mapped to a 0-10 scale for this evaluation, becoming 0, 5, and 10, respectively.'",
"note": "Primary protocol is regression/correlation, NOT argmax classification. Accuracy figures appear only anecdotally in the abstract."
},
"labels_parquet": {
"path": "/e/data1/datasets/playground/mmlaion/schuhmann1/dramabox/headspub/bench/emonet/labels.parquet",
"n_rows": 12600,
"columns": [
"clip_id",
"audio_path",
"parquet_file",
"row_index",
"rel_path",
"label",
"label_raw",
"head_name",
"n_annotators",
"ratings",
"intensity_mean",
"intensity_median",
"intensity_majority",
"intensity_min",
"intensity_max",
"gold_0_10",
"unanimous",
"present_any",
"present_all",
"duration_sec",
"sample_rate",
"audio_bytes"
],
"how_to_get_audio": "open <parquet_file> with pyarrow, take row <row_index> of column audioId -> {'bytes': mp3, 'path': name}. rel_path encodes 'file#row_index'."
},
"head_mapping": {
"Affection": "Affection",
"Amusement": "Amusement",
"Anger": "Anger",
"Arousal": "Arousal",
"Astonishment": "Astonishment_Surprise",
"Authenticity": "Authenticity",
"Awe": "Awe",
"Bitterness": "Bitterness",
"Concentration": "Concentration",
"Confusion": "Confusion",
"Contemplation": "Contemplation",
"Contempt": "Contempt",
"Contentment": "Contentment",
"Disappointment": "Disappointment",
"Disgust": "Disgust",
"Distress": "Distress",
"Doubt": "Doubt",
"Elation": "Elation",
"Embarrassment": "Embarrassment",
"Emotional Numbness": "Emotional_Numbness",
"Fatigue": "Fatigue_Exhaustion",
"Fear": "Fear",
"Helplessness": "Helplessness",
"Hope": "Hope_Enthusiasm_Optimism",
"Impatience and Irritability": "Impatience_and_Irritability",
"Infatuation": "Infatuation",
"Interest": "Interest",
"Intoxication": "Intoxication_Altered_States_of_Consciousness",
"Jealousy & Envy": "Jealousy_&_Envy",
"Longing": "Longing",
"Malevolence": "Malevolence_Malice",
"Pain": "Pain",
"Pleasure": "Pleasure_Ecstasy",
"Pride": "Pride",
"Relief": "Relief",
"Sadness": "Sadness",
"Sexual Lust": "Sexual_Lust",
"Shame": "Shame",
"Sourness": "Sourness",
"Teasing": "Teasing",
"Thankfulness": "Thankfulness_Gratitude",
"Triumph": "Triumph"
},
"heads_unused": [
"Age",
"Background_Noise",
"Confident_vs._Hesitant",
"Gender",
"High-Pitched_vs._Low-Pitched",
"Monotone_vs._Expressive",
"Recording_Quality",
"Serious_vs._Humorous",
"Soft_vs._Harsh",
"Submissive_vs._Dominant",
"Valence",
"Vulnerable_vs._Emotionally_Detached",
"Warm_vs._Cold",
"duration",
"score_background_quality",
"score_content_enjoyment",
"score_overall_quality",
"score_speech_quality",
"talking_speed"
]
}