o %Ý«i€ ã@s8dZdd„Zdd„Zdd„Zdd„Zd d „Zd d „Zd S)zžCalculates Emotion Diarization Error Rate (EDER) which is the sum of Missed Emotion (ME), False Alarm (FA), and Confusion (CF). Authors * Yingzhi Wang 2023 csÐt|ƒ}g}tt|ƒƒD]‰|ˆ}||}| ||||ˆg¡q t|ƒ}t|ƒdkr0t|ƒ}t|||ƒ} d} | D]'‰‡fdd„|Dƒ} ˆdˆdg} | D]} t| | d| dgƒ}| |7} qOq:d| |S)aÌCalculates the EDER value Arguments --------- prediction: list a list of frame-wise predictions of the utterance id: str id of the utterance duration: float duration of the utterance emotion: list of dicts the ground truth emotion and its duration, e.g. [{'emo': 'angry', 'start': 1.016, 'end': 6.336}] window_length: float the frame length used for frame-wise prediction stride: float the frame length used for frame-wise prediction Returns ------- float: the calculated EDER for the utterance Example ------- >>> from speechbrain.utils.EDER import EDER >>> prediction=['n', 'n', 'n', 'a', 'a', 'a'] >>> id="spk1_1" >>> duration=1.22 >>> emotion=[{'emo': 'angry', 'start': 0.39, 'end': 1.10}] >>> window_length = 0.2 >>> stride = 0.2 >>> EDER(prediction, id, duration, emotion, window_length, stride) 0.2704918032786885 éécs g|] }|dˆdkr|‘qS)é©)Ú.0Úelement©ÚirúJ/home/ubuntu/.local/lib/python3.10/site-packages/speechbrain/utils/EDER.pyÚ ;s zEDER..é)ÚfloatÚrangeÚlenÚappendÚ!merge_ssegs_same_emotion_adjacentÚdistribute_overlapÚreference_to_lolÚ getOverlap)Ú predictionÚidÚdurationÚemotionÚ window_lengthÚstrideÚlolÚstartÚendÚrefÚ good_predsÚ candidatesÚ ref_intervalÚ candidateÚoverlaprrr ÚEDER s&#   þ r#cCs*tdt|d|dƒt|d|dƒƒS)aVGet the overlapped length of two intervals Arguments --------- a : list b : list Returns ------- float: overlapped length Example ------- >>> from speechbrain.utils.EDER import getOverlap >>> interval1=[1.2, 3.4] >>> interval2=[2.3, 4.5] >>> getOverlap(interval1, interval2) 1.1 rr)ÚmaxÚmin)ÚaÚbrrr rDs*rcCs||krdSdS)aÔReturns True if segments are overlapping. Arguments --------- end1 : float End time of the first segment. start2 : float Start time of the second segment. Returns ------- overlapped : bool True of segments overlapped else False. Example ------- >>> from speechbrain.processing import diarization as diar >>> diar.is_overlapped(5.5, 3.4) True >>> diar.is_overlapped(5.5, 6.4) False FTr)Úend1Ústart2rrr Ú is_overlapped[sr*cCs¢g}|d}d}tdt|ƒƒD]4}||}t|d|dƒr<|d|dkr<|d|d<|t|ƒdkr;d}| |¡q| |¡|}q|durO| |d¡|S)aÛMerge adjacent sub-segs if they are the same emotion. Arguments --------- lol : list of list Each list contains [utt_id, sseg_start, sseg_end, emo_label]. Returns ------- new_lol : list of list new_lol contains adjacent segments merged from the same emotion ID. Example ------- >>> from speechbrain.utils.EDER import merge_ssegs_same_emotion_adjacent >>> lol=[['u1', 0.0, 7.0, 'a'], ... ['u1', 7.0, 9.0, 'a'], ... ['u1', 9.0, 11.0, 'n'], ... ['u1', 11.0, 13.0, 'n'], ... ['u1', 13.0, 15.0, 'n'], ... ['u1', 15.0, 16.0, 'a']] >>> merge_ssegs_same_emotion_adjacent(lol) [['u1', 0.0, 9.0, 'a'], ['u1', 9.0, 15.0, 'n'], ['u1', 15.0, 16.0, 'a']] rFrr rTéÿÿÿÿ©r rr*r)rÚnew_lolÚssegÚflagrÚ next_ssegrrr rxs "  € rcCsŽt|ƒdks Jdƒ‚g}|dd}|dd}|dkr%| |d|dg¡| ||||dddg¡t|ƒ}||krE| |||dg¡|S)aèChange reference to a list of list Arguments --------- id: str id of the utterance duration: float duration of the utterance emotion: list of dicts the ground truth emotion and its duration, e.g. [{'emo': 'angry', 'start': 1.016, 'end': 6.336}] Returns ------- lol : list of list It has each list structure as [rec_id, sseg_start, sseg_end, spkr_id]. Example ------- >>> from speechbrain.utils.EDER import reference_to_lol >>> id="u1" >>> duration=8.0 >>> emotion=[{'emo': 'angry', 'start': 1.016, 'end': 6.336}] >>> reference_to_lol(id, duration, emotion) [['u1', 0, 1.016, 'n'], ['u1', 1.016, 6.336, 'a'], ['u1', 6.336, 8.0, 'n']] rzXNotImplementedError: The solution is only implemented for one-emotion utterance for now.rrrÚnÚemo)rrr )rrrrrrrrr r©sÿ  rcCsæg}|d}tdt|ƒƒD]^}||}t|d|dƒrR|d|d}|d|d|d<|d|d|d<t|ƒdkrD| |¡n |d|krO| |¡|}q t|ƒdkr^| |¡n |d|kri| |¡|}q | |¡|S)a Distributes the overlapped speech equally among the adjacent segments with different emotions. Arguments --------- lol : list of list It has each list structure as [rec_id, sseg_start, sseg_end, spkr_id]. Returns ------- new_lol : list of list It contains the overlapped part equally divided among the adjacent segments with different emotion IDs. Example ------- >>> from speechbrain.processing import diarization as diar >>> lol = [['r1', 5.5, 9.0, 's1'], ... ['r1', 8.0, 11.0, 's2'], ... ['r1', 11.5, 13.0, 's2'], ... ['r1', 12.0, 15.0, 's1']] >>> diar.distribute_overlap(lol) [['r1', 5.5, 8.5, 's1'], ['r1', 8.5, 11.0, 's2'], ['r1', 11.5, 12.5, 's2'], ['r1', 12.5, 15.0, 's1']] rrr g@r+r,)rr-r.rr0r"rrr rÕs(         rN)Ú__doc__r#rr*rrrrrrr Ús;1 ,