One complete Gemini audio annotation

{
  "schema_version": "laion-gemini-voice-annotations-v1",
  "sha256_mp3": "00003c59c3999f3d6a0ebbe97bce67053785d09a0e67988ded26bf19035f1938",
  "duration_s": 10.219,
  "split": "train",
  "source_family": "s1",
  "source_url": "https://huggingface.co/datasets/laion/tts-scaling-ladder-de-en",
  "source_memberships": [
    {
      "source": "S1_100h",
      "bucket": 369,
      "uid": "mediathek_0181__V__RANG__extremely_low__en.c019.k0"
    }
  ],
  "source_detail": {
    "source_dataset": "vc_sidon",
    "hf_source": "laion/laion-voice-profiles-annotated (vc_sidon)",
    "license": "CC-BY-4.0",
    "uid": "mediathek_0181__V__RANG__extremely_low__en.c019.k0",
    "selection_reason": "quota_random"
  },
  "annotation_license": "CC-BY-4.0",
  "audio_in_shard": true,
  "source_audio_license": "cc-by-4.0",
  "gemini_annotation": {
    "language": "Russian",
    "accent": "Russian",
    "transcript": "Всё врут.",
    "voicenet": {
      "temp": 1,
      "chnk": 0,
      "smth": 2,
      "clrt": 2,
      "rang": 1,
      "emph": 2,
      "dflu": 0,
      "stru": 3,
      "stnc": 1,
      "focs": 1,
      "vuln": 4,
      "gend": 5,
      "agev": 5,
      "regs": 1,
      "valn": 1,
      "arou": 1,
      "volt": 1,
      "resp": 5,
      "tens": 4,
      "cogl": 2,
      "atck": 2,
      "brgt": 2,
      "roug": 5,
      "harm": 1,
      "full": 2,
      "warm": 2,
      "metl": 1,
      "esth": 2,
      "vflx": 3,
      "darc": 2,
      "arsh": 2,
      "vals": 2,
      "rcql": 3,
      "bkgn": 3,
      "expl": 0,
      "r_chst": 3,
      "r_thrt": 4,
      "r_oral": 2,
      "r_mask": 1,
      "r_nasl": 1,
      "r_head": 1,
      "r_mixd": 2,
      "s_casu": 3,
      "s_conv": 1,
      "s_form": 0,
      "s_dram": 4,
      "s_narr": 0,
      "s_news": 0,
      "s_tech": 0,
      "s_auth": 1,
      "s_play": 0,
      "s_cart": 0,
      "s_asmr": 2,
      "s_whis": 4,
      "s_rant": 1,
      "s_stry": 1,
      "s_mono": 5
    },
    "emonet": {
      "amusement": 0,
      "elation": 0,
      "pleasure_ecstasy": 0,
      "contentment": 0,
      "gratitude": 0,
      "affection": 0,
      "infatuation": 0,
      "hope_optimism": 0,
      "triumph": 0,
      "pride": 0,
      "interest": 0,
      "awe": 0,
      "astonishment_surprise": 0,
      "concentration": 1,
      "contemplation": 3,
      "relief": 0,
      "longing": 1,
      "teasing": 0,
      "impatience_irritability": 1,
      "sexual_lust": 0,
      "doubt": 2,
      "fear": 0,
      "distress": 2,
      "confusion": 0,
      "embarrassment": 0,
      "shame": 0,
      "disappointment": 3,
      "sadness": 2,
      "bitterness": 3,
      "contempt": 2,
      "disgust": 1,
      "anger": 1,
      "malevolence_malice": 0,
      "sourness": 2,
      "pain": 2,
      "helplessness": 2,
      "fatigue_exhaustion": 4,
      "emotional_numbness": 2,
      "intoxication_altered_states": 1,
      "jealousy_envy": 0
    },
    "genuineness": 5,
    "vocal_burst_blend": 8,
    "vocal_burst_count": 3,
    "vocal_bursts": [
      {
        "i": 1,
        "start": 0.0,
        "end": 1.95,
        "fine": "Heavy Breathing",
        "group23": "breath_fast",
        "caption": "A slow, labored, and deep breath intake followed by a weary exhalation with noticeable throat friction and vocal fry, establishing a state of deep physical exhaustion and quiet distress before any speech occurs."
      },
      {
        "i": 2,
        "start": 2.05,
        "end": 4.5,
        "fine": "Exasperated Sigh",
        "group23": "sigh_neg",
        "caption": "A pronounced, breathy puff and weary sigh with audible lip and throat friction, beginning with a soft voiceless release ('pfft') that conveys deep frustration and physical weariness directly leading toward the spoken phrase."
      },
      {
        "i": 3,
        "start": 6.8,
        "end": 9.8,
        "fine": "Heavy Breathing",
        "group23": "breath_fast",
        "caption": "Extended, faint, labored post-utterance breathing and soft trailing exhalations that continue in the background silence after the whispered words, demonstrating natural physiological recovery and sustained exhaustion."
      }
    ],
    "caption": "A mature adult or older male-coded speaker delivers a single, brief Russian phrase preceded and followed by heavy, exhausted respiration. The acoustic profile is dominated by severe vocal fatigue, low energy, and deep respiratory labor, featuring rough, gravelly vocal fry and a predominantly whispered, half-voiced phonation centered in the throat and chest. Prior to the words, the speaker emits long, strained breathing and an exasperated, breathy sigh. The two spoken words are delivered quietly, almost inwardly like a private bitter realization, with restrained pitch and low volume. The overall tone carries strong bitterness, disappointment, and exhaustion, sounding naturalistic and lived-in within a dry, clean recording environment.",
    "director_caption": "Sit in heavy physical and emotional exhaustion. Before speaking, let out a slow, deep, strained breath with audible throat friction. Follow it immediately with a soft, dismissive puff of breath and an exasperated, weary sigh. Barely muster the energy to speak, keeping the voice down to an intimate, gravelly, raspy whisper colored by bitter disillusionment and pain: \"Всё врут.\" Do not project; let the final consonant trail off weakly into the room, followed by faint, labored breathing as if drained of all strength."
  },
  "gemini_provenance": {
    "annotation_model": "gemini-3.8-flash",
    "prompt_sha256": "18bc5ffcb1ce9cfe4dfbe1848c447fd8081384acfcc713c50f28254df4799911",
    "batch_tag": "canary",
    "batch_name": "batches/bsmt6kwc0kon22p9rz8z0cyph0w26n7cobif"
  },
  "scalar_targets_raw": {
    "emo_Affection": 0,
    "emo_Amusement": 0,
    "emo_Anger": 1,
    "emo_Astonishment_Surprise": 0,
    "emo_Awe": 0,
    "emo_Bitterness": 3,
    "emo_Concentration": 1,
    "emo_Confusion": 0,
    "emo_Contemplation": 3,
    "emo_Contempt": 2,
    "emo_Contentment": 0,
    "emo_Disappointment": 3,
    "emo_Disgust": 1,
    "emo_Distress": 2,
    "emo_Doubt": 2,
    "emo_Elation": 0,
    "emo_Embarrassment": 0,
    "emo_Emotional_Numbness": 2,
    "emo_Fatigue_Exhaustion": 4,
    "emo_Fear": 0,
    "emo_Helplessness": 2,
    "emo_Hope_Enthusiasm_Optimism": 0,
    "emo_Impatience_and_Irritability": 1,
    "emo_Infatuation": 0,
    "emo_Interest": 0,
    "emo_Intoxication_Altered_States_of_Consciousness": 1,
    "emo_Jealousy_and_Envy": 0,
    "emo_Longing": 1,
    "emo_Malevolence_Malice": 0,
    "emo_Pain": 2,
    "emo_Pleasure_Ecstasy": 0,
    "emo_Pride": 0,
    "emo_Relief": 0,
    "emo_Sadness": 2,
    "emo_Sexual_Lust": 0,
    "emo_Shame": 0,
    "emo_Sourness": 2,
    "emo_Teasing": 0,
    "emo_Thankfulness_Gratitude": 0,
    "emo_Triumph": 0,
    "vn_AGEV_reg": 5,
    "vn_AROU_reg": 1,
    "vn_ARSH_reg": 2,
    "vn_ATCK_reg": 2,
    "vn_BKGN_reg": 3,
    "vn_BRGT_reg": 2,
    "vn_CHNK_reg": 0,
    "vn_CLRT_reg": 2,
    "vn_COGL_reg": 2,
    "vn_DARC_reg": 2,
    "vn_DFLU_reg": 0,
    "vn_EMPH_reg": 2,
    "vn_ESTH_reg": 2,
    "vn_EXPL_reg": 0,
    "vn_FOCS_reg": 1,
    "vn_FULL_reg": 2,
    "vn_GEND_reg": 5,
    "vn_HARM_reg": 1,
    "vn_METL_reg": 1,
    "vn_RANG_reg": 1,
    "vn_RCQL_reg": 3,
    "vn_REGS_reg": 1,
    "vn_RESP_reg": 5,
    "vn_ROUG_reg": 5,
    "vn_R_CHST_reg": 3,
    "vn_R_HEAD_reg": 1,
    "vn_R_MASK_reg": 1,
    "vn_R_MIXD_reg": 2,
    "vn_R_NASL_reg": 1,
    "vn_R_ORAL_reg": 2,
    "vn_R_THRT_reg": 4,
    "vn_SMTH_reg": 2,
    "vn_STNC_reg": 1,
    "vn_STRU_reg": 3,
    "vn_S_ASMR_reg": 2,
    "vn_S_AUTH_reg": 1,
    "vn_S_CART_reg": 0,
    "vn_S_CASU_reg": 3,
    "vn_S_CONV_reg": 1,
    "vn_S_DRAM_reg": 4,
    "vn_S_FORM_reg": 0,
    "vn_S_MONO_reg": 5,
    "vn_S_NARR_reg": 0,
    "vn_S_NEWS_reg": 0,
    "vn_S_PLAY_reg": 0,
    "vn_S_RANT_reg": 1,
    "vn_S_STRY_reg": 1,
    "vn_S_TECH_reg": 0,
    "vn_S_WHIS_reg": 4,
    "vn_TEMP_reg": 1,
    "vn_TENS_reg": 4,
    "vn_VALN_reg": 1,
    "vn_VALS_reg": 2,
    "vn_VFLX_reg": 3,
    "vn_VOLT_reg": 1,
    "vn_VULN_reg": 4,
    "vn_WARM_reg": 2,
    "genuineness_0_6": 5,
    "blend_0_10": 8,
    "R_quality": 1.0888671875,
    "voiceclap_attribute:Affection": 0,
    "voiceclap_attribute:Background_Noise": 0.5198580622673035,
    "voiceclap_attribute:Disappointment": 3,
    "voiceclap_attribute:Fear": 0,
    "voiceclap_attribute:Intoxication_Altered_States_of_Consciousness": 1,
    "voiceclap_attribute:Recording_Quality": 1.7628860473632812,
    "voiceclap_attribute:Submissive_vs._Dominant": -0.0239865779876709,
    "voiceclap_attribute:score_content_enjoyment": 4.339709281921387,
    "voiceclap_attribute:Age": 3.149357795715332,
    "voiceclap_attribute:Bitterness": 3,
    "voiceclap_attribute:Disgust": 1,
    "voiceclap_attribute:Gender": -0.0775860846042633,
    "voiceclap_attribute:Jealousy_&_Envy": 0,
    "voiceclap_attribute:Relief": 0,
    "voiceclap_attribute:Teasing": 0,
    "voiceclap_attribute:score_overall_quality": 2.2789881229400635,
    "voiceclap_attribute:Amusement": 0,
    "voiceclap_attribute:Concentration": 1,
    "voiceclap_attribute:Distress": 2,
    "voiceclap_attribute:Helplessness": 2,
    "voiceclap_attribute:Longing": 1,
    "voiceclap_attribute:Sadness": 2,
    "voiceclap_attribute:Thankfulness_Gratitude": 0,
    "voiceclap_attribute:score_speech_quality": 1.8975639343261719,
    "voiceclap_attribute:Anger": 1,
    "voiceclap_attribute:Confident_vs._Hesitant": 1.5903536081314087,
    "voiceclap_attribute:Doubt": 2,
    "voiceclap_attribute:High-Pitched_vs._Low-Pitched": 1.5755666494369507,
    "voiceclap_attribute:Malevolence_Malice": 0,
    "voiceclap_attribute:Serious_vs._Humorous": 0.4416743516921997,
    "voiceclap_attribute:Triumph": 0,
    "voiceclap_attribute:duration": 7.923616409301758,
    "voiceclap_attribute:Arousal": 1.3691121339797974,
    "voiceclap_attribute:Confusion": 0,
    "voiceclap_attribute:Elation": 0,
    "voiceclap_attribute:Hope_Enthusiasm_Optimism": 0,
    "voiceclap_attribute:Monotone_vs._Expressive": 1.1926519870758057,
    "voiceclap_attribute:Sexual_Lust": 0,
    "voiceclap_attribute:Valence": -1.1105155944824219,
    "voiceclap_attribute:talking_speed": 3.410037040710449,
    "voiceclap_attribute:Astonishment_Surprise": 0,
    "voiceclap_attribute:Contemplation": 3,
    "voiceclap_attribute:Embarrassment": 0,
    "voiceclap_attribute:Impatience_and_Irritability": 1,
    "voiceclap_attribute:Pain": 2,
    "voiceclap_attribute:Shame": 0,
    "voiceclap_attribute:Vulnerable_vs._Emotionally_Detached": 0.8524438142776489,
    "voiceclap_attribute:Authenticity": 2.909477949142456,
    "voiceclap_attribute:Contempt": 2,
    "voiceclap_attribute:Emotional_Numbness": 2,
    "voiceclap_attribute:Infatuation": 0,
    "voiceclap_attribute:Pleasure_Ecstasy": 0,
    "voiceclap_attribute:Soft_vs._Harsh": 0.6552486419677734,
    "voiceclap_attribute:Warm_vs._Cold": -0.22793370485305786,
    "voiceclap_attribute:Awe": 0,
    "voiceclap_attribute:Contentment": 0,
    "voiceclap_attribute:Fatigue_Exhaustion": 4,
    "voiceclap_attribute:Interest": 0,
    "voiceclap_attribute:Pride": 0,
    "voiceclap_attribute:Sourness": 2,
    "voiceclap_attribute:score_background_quality": 3.3156840801239014,
    "audiobox:CE": 3.82999,
    "audiobox:CU": 5.75418,
    "audiobox:PC": 1.96954,
    "audiobox:PQ": 7.49823,
    "dnsmos:SIG_raw": 3.24539,
    "dnsmos:BAK_raw": 3.89919,
    "dnsmos:OVRL_raw": 2.91806,
    "dnsmos:SIG": 3.0829,
    "dnsmos:BAK": 3.8765,
    "dnsmos:OVRL": 2.72486,
    "dnsmos:P808_MOS": 3.15419,
    "eiv_extra:Age": 3.438810110092163,
    "eiv_extra:Arousal": 1.0481913089752197,
    "eiv_extra:Authenticity": 2.692965507507324,
    "eiv_extra:Background_Noise": 0.8105835318565369,
    "eiv_extra:Confident_vs._Hesitant": 2.226170301437378,
    "eiv_extra:Gender": -0.03504212945699692,
    "eiv_extra:High-Pitched_vs._Low-Pitched": 2.09500789642334,
    "eiv_extra:Monotone_vs._Expressive": 1.261232852935791,
    "eiv_extra:Recording_Quality": 1.3177694082260132,
    "eiv_extra:Serious_vs._Humorous": 0.038688793778419495,
    "eiv_extra:Soft_vs._Harsh": 1.2463370561599731,
    "eiv_extra:Submissive_vs._Dominant": -0.49340391159057617,
    "eiv_extra:Valence": -1.4189921617507935,
    "eiv_extra:Vulnerable_vs._Emotionally_Detached": 1.2982590198516846,
    "eiv_extra:Warm_vs._Cold": -0.42472782731056213,
    "eiv_extra:score_background_quality": 3.3467822074890137,
    "eiv_extra:score_content_enjoyment": 3.6916821002960205,
    "eiv_extra:score_overall_quality": 1.968508243560791,
    "eiv_extra:score_speech_quality": 1.6834155321121216,
    "burst_count_log1p": 1.3862943611198906
  },
  "scalar_target_provenance": {
    "emo_Affection": "gemini-3.8-flash",
    "emo_Amusement": "gemini-3.8-flash",
    "emo_Anger": "gemini-3.8-flash",
    "emo_Astonishment_Surprise": "gemini-3.8-flash",
    "emo_Awe": "gemini-3.8-flash",
    "emo_Bitterness": "gemini-3.8-flash",
    "emo_Concentration": "gemini-3.8-flash",
    "emo_Confusion": "gemini-3.8-flash",
    "emo_Contemplation": "gemini-3.8-flash",
    "emo_Contempt": "gemini-3.8-flash",
    "emo_Contentment": "gemini-3.8-flash",
    "emo_Disappointment": "gemini-3.8-flash",
    "emo_Disgust": "gemini-3.8-flash",
    "emo_Distress": "gemini-3.8-flash",
    "emo_Doubt": "gemini-3.8-flash",
    "emo_Elation": "gemini-3.8-flash",
    "emo_Embarrassment": "gemini-3.8-flash",
    "emo_Emotional_Numbness": "gemini-3.8-flash",
    "emo_Fatigue_Exhaustion": "gemini-3.8-flash",
    "emo_Fear": "gemini-3.8-flash",
    "emo_Helplessness": "gemini-3.8-flash",
    "emo_Hope_Enthusiasm_Optimism": "gemini-3.8-flash",
    "emo_Impatience_and_Irritability": "gemini-3.8-flash",
    "emo_Infatuation": "gemini-3.8-flash",
    "emo_Interest": "gemini-3.8-flash",
    "emo_Intoxication_Altered_States_of_Consciousness": "gemini-3.8-flash",
    "emo_Jealousy_and_Envy": "gemini-3.8-flash",
    "emo_Longing": "gemini-3.8-flash",
    "emo_Malevolence_Malice": "gemini-3.8-flash",
    "emo_Pain": "gemini-3.8-flash",
    "emo_Pleasure_Ecstasy": "gemini-3.8-flash",
    "emo_Pride": "gemini-3.8-flash",
    "emo_Relief": "gemini-3.8-flash",
    "emo_Sadness": "gemini-3.8-flash",
    "emo_Sexual_Lust": "gemini-3.8-flash",
    "emo_Shame": "gemini-3.8-flash",
    "emo_Sourness": "gemini-3.8-flash",
    "emo_Teasing": "gemini-3.8-flash",
    "emo_Thankfulness_Gratitude": "gemini-3.8-flash",
    "emo_Triumph": "gemini-3.8-flash",
    "vn_AGEV_reg": "gemini-3.8-flash",
    "vn_AROU_reg": "gemini-3.8-flash",
    "vn_ARSH_reg": "gemini-3.8-flash",
    "vn_ATCK_reg": "gemini-3.8-flash",
    "vn_BKGN_reg": "gemini-3.8-flash",
    "vn_BRGT_reg": "gemini-3.8-flash",
    "vn_CHNK_reg": "gemini-3.8-flash",
    "vn_CLRT_reg": "gemini-3.8-flash",
    "vn_COGL_reg": "gemini-3.8-flash",
    "vn_DARC_reg": "gemini-3.8-flash",
    "vn_DFLU_reg": "gemini-3.8-flash",
    "vn_EMPH_reg": "gemini-3.8-flash",
    "vn_ESTH_reg": "gemini-3.8-flash",
    "vn_EXPL_reg": "gemini-3.8-flash",
    "vn_FOCS_reg": "gemini-3.8-flash",
    "vn_FULL_reg": "gemini-3.8-flash",
    "vn_GEND_reg": "gemini-3.8-flash",
    "vn_HARM_reg": "gemini-3.8-flash",
    "vn_METL_reg": "gemini-3.8-flash",
    "vn_RANG_reg": "gemini-3.8-flash",
    "vn_RCQL_reg": "gemini-3.8-flash",
    "vn_REGS_reg": "gemini-3.8-flash",
    "vn_RESP_reg": "gemini-3.8-flash",
    "vn_ROUG_reg": "gemini-3.8-flash",
    "vn_R_CHST_reg": "gemini-3.8-flash",
    "vn_R_HEAD_reg": "gemini-3.8-flash",
    "vn_R_MASK_reg": "gemini-3.8-flash",
    "vn_R_MIXD_reg": "gemini-3.8-flash",
    "vn_R_NASL_reg": "gemini-3.8-flash",
    "vn_R_ORAL_reg": "gemini-3.8-flash",
    "vn_R_THRT_reg": "gemini-3.8-flash",
    "vn_SMTH_reg": "gemini-3.8-flash",
    "vn_STNC_reg": "gemini-3.8-flash",
    "vn_STRU_reg": "gemini-3.8-flash",
    "vn_S_ASMR_reg": "gemini-3.8-flash",
    "vn_S_AUTH_reg": "gemini-3.8-flash",
    "vn_S_CART_reg": "gemini-3.8-flash",
    "vn_S_CASU_reg": "gemini-3.8-flash",
    "vn_S_CONV_reg": "gemini-3.8-flash",
    "vn_S_DRAM_reg": "gemini-3.8-flash",
    "vn_S_FORM_reg": "gemini-3.8-flash",
    "vn_S_MONO_reg": "gemini-3.8-flash",
    "vn_S_NARR_reg": "gemini-3.8-flash",
    "vn_S_NEWS_reg": "gemini-3.8-flash",
    "vn_S_PLAY_reg": "gemini-3.8-flash",
    "vn_S_RANT_reg": "gemini-3.8-flash",
    "vn_S_STRY_reg": "gemini-3.8-flash",
    "vn_S_TECH_reg": "gemini-3.8-flash",
    "vn_S_WHIS_reg": "gemini-3.8-flash",
    "vn_TEMP_reg": "gemini-3.8-flash",
    "vn_TENS_reg": "gemini-3.8-flash",
    "vn_VALN_reg": "gemini-3.8-flash",
    "vn_VALS_reg": "gemini-3.8-flash",
    "vn_VFLX_reg": "gemini-3.8-flash",
    "vn_VOLT_reg": "gemini-3.8-flash",
    "vn_VULN_reg": "gemini-3.8-flash",
    "vn_WARM_reg": "gemini-3.8-flash",
    "genuineness_0_6": "gemini-3.8-flash",
    "blend_0_10": "gemini-3.8-flash",
    "R_quality": "original_source_metadata",
    "voiceclap_attribute:Affection": "gemini-3.8-flash",
    "voiceclap_attribute:Background_Noise": "teacher_sidecar",
    "voiceclap_attribute:Disappointment": "gemini-3.8-flash",
    "voiceclap_attribute:Fear": "gemini-3.8-flash",
    "voiceclap_attribute:Intoxication_Altered_States_of_Consciousness": "gemini-3.8-flash",
    "voiceclap_attribute:Recording_Quality": "teacher_sidecar",
    "voiceclap_attribute:Submissive_vs._Dominant": "teacher_sidecar",
    "voiceclap_attribute:score_content_enjoyment": "teacher_sidecar",
    "voiceclap_attribute:Age": "teacher_sidecar",
    "voiceclap_attribute:Bitterness": "gemini-3.8-flash",
    "voiceclap_attribute:Disgust": "gemini-3.8-flash",
    "voiceclap_attribute:Gender": "teacher_sidecar",
    "voiceclap_attribute:Jealousy_&_Envy": "gemini-3.8-flash",
    "voiceclap_attribute:Relief": "gemini-3.8-flash",
    "voiceclap_attribute:Teasing": "gemini-3.8-flash",
    "voiceclap_attribute:score_overall_quality": "teacher_sidecar",
    "voiceclap_attribute:Amusement": "gemini-3.8-flash",
    "voiceclap_attribute:Concentration": "gemini-3.8-flash",
    "voiceclap_attribute:Distress": "gemini-3.8-flash",
    "voiceclap_attribute:Helplessness": "gemini-3.8-flash",
    "voiceclap_attribute:Longing": "gemini-3.8-flash",
    "voiceclap_attribute:Sadness": "gemini-3.8-flash",
    "voiceclap_attribute:Thankfulness_Gratitude": "gemini-3.8-flash",
    "voiceclap_attribute:score_speech_quality": "teacher_sidecar",
    "voiceclap_attribute:Anger": "gemini-3.8-flash",
    "voiceclap_attribute:Confident_vs._Hesitant": "teacher_sidecar",
    "voiceclap_attribute:Doubt": "gemini-3.8-flash",
    "voiceclap_attribute:High-Pitched_vs._Low-Pitched": "teacher_sidecar",
    "voiceclap_attribute:Malevolence_Malice": "gemini-3.8-flash",
    "voiceclap_attribute:Serious_vs._Humorous": "teacher_sidecar",
    "voiceclap_attribute:Triumph": "gemini-3.8-flash",
    "voiceclap_attribute:duration": "teacher_sidecar",
    "voiceclap_attribute:Arousal": "teacher_sidecar",
    "voiceclap_attribute:Confusion": "gemini-3.8-flash",
    "voiceclap_attribute:Elation": "gemini-3.8-flash",
    "voiceclap_attribute:Hope_Enthusiasm_Optimism": "gemini-3.8-flash",
    "voiceclap_attribute:Monotone_vs._Expressive": "teacher_sidecar",
    "voiceclap_attribute:Sexual_Lust": "gemini-3.8-flash",
    "voiceclap_attribute:Valence": "teacher_sidecar",
    "voiceclap_attribute:talking_speed": "teacher_sidecar",
    "voiceclap_attribute:Astonishment_Surprise": "gemini-3.8-flash",
    "voiceclap_attribute:Contemplation": "gemini-3.8-flash",
    "voiceclap_attribute:Embarrassment": "gemini-3.8-flash",
    "voiceclap_attribute:Impatience_and_Irritability": "gemini-3.8-flash",
    "voiceclap_attribute:Pain": "gemini-3.8-flash",
    "voiceclap_attribute:Shame": "gemini-3.8-flash",
    "voiceclap_attribute:Vulnerable_vs._Emotionally_Detached": "teacher_sidecar",
    "voiceclap_attribute:Authenticity": "teacher_sidecar",
    "voiceclap_attribute:Contempt": "gemini-3.8-flash",
    "voiceclap_attribute:Emotional_Numbness": "gemini-3.8-flash",
    "voiceclap_attribute:Infatuation": "gemini-3.8-flash",
    "voiceclap_attribute:Pleasure_Ecstasy": "gemini-3.8-flash",
    "voiceclap_attribute:Soft_vs._Harsh": "teacher_sidecar",
    "voiceclap_attribute:Warm_vs._Cold": "teacher_sidecar",
    "voiceclap_attribute:Awe": "gemini-3.8-flash",
    "voiceclap_attribute:Contentment": "gemini-3.8-flash",
    "voiceclap_attribute:Fatigue_Exhaustion": "gemini-3.8-flash",
    "voiceclap_attribute:Interest": "gemini-3.8-flash",
    "voiceclap_attribute:Pride": "gemini-3.8-flash",
    "voiceclap_attribute:Sourness": "gemini-3.8-flash",
    "voiceclap_attribute:score_background_quality": "teacher_sidecar",
    "audiobox:CE": "teacher_sidecar",
    "audiobox:CU": "teacher_sidecar",
    "audiobox:PC": "teacher_sidecar",
    "audiobox:PQ": "teacher_sidecar",
    "dnsmos:SIG_raw": "teacher_sidecar",
    "dnsmos:BAK_raw": "teacher_sidecar",
    "dnsmos:OVRL_raw": "teacher_sidecar",
    "dnsmos:SIG": "teacher_sidecar",
    "dnsmos:BAK": "teacher_sidecar",
    "dnsmos:OVRL": "teacher_sidecar",
    "dnsmos:P808_MOS": "teacher_sidecar",
    "eiv_extra:Age": "teacher_sidecar",
    "eiv_extra:Arousal": "teacher_sidecar",
    "eiv_extra:Authenticity": "teacher_sidecar",
    "eiv_extra:Background_Noise": "teacher_sidecar",
    "eiv_extra:Confident_vs._Hesitant": "teacher_sidecar",
    "eiv_extra:Gender": "teacher_sidecar",
    "eiv_extra:High-Pitched_vs._Low-Pitched": "teacher_sidecar",
    "eiv_extra:Monotone_vs._Expressive": "teacher_sidecar",
    "eiv_extra:Recording_Quality": "teacher_sidecar",
    "eiv_extra:Serious_vs._Humorous": "teacher_sidecar",
    "eiv_extra:Soft_vs._Harsh": "teacher_sidecar",
    "eiv_extra:Submissive_vs._Dominant": "teacher_sidecar",
    "eiv_extra:Valence": "teacher_sidecar",
    "eiv_extra:Vulnerable_vs._Emotionally_Detached": "teacher_sidecar",
    "eiv_extra:Warm_vs._Cold": "teacher_sidecar",
    "eiv_extra:score_background_quality": "teacher_sidecar",
    "eiv_extra:score_content_enjoyment": "teacher_sidecar",
    "eiv_extra:score_overall_quality": "teacher_sidecar",
    "eiv_extra:score_speech_quality": "teacher_sidecar",
    "burst_count_log1p": "gemini-3.8-flash"
  },
  "characters_per_second": 0.8807123984734319,
  "cps_source": "gemini_transcript",
  "vocal_burst_events": [
    {
      "i": 1,
      "start": 0.0,
      "end": 1.95,
      "fine": "Heavy Breathing",
      "group23": "breath_fast",
      "caption": "A slow, labored, and deep breath intake followed by a weary exhalation with noticeable throat friction and vocal fry, establishing a state of deep physical exhaustion and quiet distress before any speech occurs.",
      "raw_end": 1.95,
      "checkpoint_class_id": 3,
      "timestamp_clamped": false
    },
    {
      "i": 2,
      "start": 2.05,
      "end": 4.5,
      "fine": "Exasperated Sigh",
      "group23": "sigh_neg",
      "caption": "A pronounced, breathy puff and weary sigh with audible lip and throat friction, beginning with a soft voiceless release ('pfft') that conveys deep frustration and physical weariness directly leading toward the spoken phrase.",
      "raw_end": 4.5,
      "checkpoint_class_id": 13,
      "timestamp_clamped": false
    },
    {
      "i": 3,
      "start": 6.8,
      "end": 9.8,
      "fine": "Heavy Breathing",
      "group23": "breath_fast",
      "caption": "Extended, faint, labored post-utterance breathing and soft trailing exhalations that continue in the background silence after the whispered words, demonstrating natural physiological recovery and sustained exhaustion.",
      "raw_end": 9.8,
      "checkpoint_class_id": 3,
      "timestamp_clamped": false
    }
  ],
  "teacher_metadata": {
    "voiceclap": {
      "voiceclap": "4e0170bf9a7e29704dd3a26ca92855b3cdd8706c",
      "voicenet": "cdafe5170561eaadb09f012ed5ae48e4f82b7b91",
      "genuineness": "36526b2264d92c61b372248253de4270791f52ee",
      "blend": "fe7086f447f1de2aeb0fbf78f02b99b9c5e5074a",
      "attribute_heads": "8441fbd4050fb670c34453d99b3fdae7e8513667",
      "speech_domain_valid": true,
      "validity_at_teacher_annotation": true,
      "current_validity_source": "latest_valid_flash_transcript_and_source_metadata"
    },
    "audiobox": {
      "model": "facebook/audiobox-aesthetics",
      "revision": "9b1dd8e5df9af7216e836a98974fe3b82c56ded6"
    },
    "dnsmos": {
      "model": "Microsoft DNSMOS non-personalized + P808",
      "code": "/e/scratch/reformo/schuhmann1_moss/code/dns-challenge/DNSMOS",
      "valid_for_speech": true,
      "window_count": 1,
      "short_audio_policy": "repeat to 9.01 s; one-second window hop",
      "validity_at_teacher_annotation": true,
      "current_validity_source": "latest_valid_flash_transcript_and_source_metadata"
    },
    "empathic": {
      "model": "laion/Empathic-Insight-Voice-Plus",
      "revision": "9ceb45912f4d555fc0210e92ec8459234b3992ec",
      "encoder_revision": "9400e6740ea103bf619a4ce66374576fab8a4e23",
      "speech_domain_valid": true,
      "validity_at_teacher_annotation": true,
      "current_validity_source": "latest_valid_flash_transcript_and_source_metadata"
    },
    "orange": {
      "timbre": "Orange/Speaker-wavLM-tbr@b8d2608d56f18e2b6e27ba566cf69132e2c2ad6c",
      "identity": "Orange/Speaker-wavLM-id@abbb3c7b8d220ceebc33d9bd3bb5aedb580342c7",
      "valid_single_speaker_target": true,
      "speaker_validity_source": "explicit_metadata_or_single_voice_synthetic_source",
      "validity_at_teacher_annotation": true,
      "current_validity_source": "latest_valid_flash_transcript_and_source_metadata"
    }
  },
  "speaker_target_valid": true,
  "embedding_file": "00003c59c3999f3d6a0ebbe97bce67053785d09a0e67988ded26bf19035f1938.npz",
  "notes": "All non-Gemini scalar/vector targets are predictions by the linked teachers, not human labels. The entire selected waveform, including any mixture, was passed to the teachers. Every vocal event has original start and end seconds."
}