{ "ckpt": "/home/agertel/work/aadd-runs/v3/aadd_v3_whisper_small_frames.pt", "synthetic": { "test_en": { "frame": { "per_class": { "noise": { "support": 78639, "auc": 0.9739364880338869, "ap": 0.8845758786765241, "f1": 0.8733835217585184, "precision": 0.9016830731317618, "recall": 0.8468062920433881 }, "music": { "support": 84000, "auc": 0.9985092503206674, "ap": 0.983359150076788, "f1": 0.9658760647082152, "precision": 0.9605146980916615, "recall": 0.971297619047619 }, "reverb": { "support": 78236, "auc": 0.9960960632414917, "ap": 0.9871238110008128, "f1": 0.9512744200244202, "precision": 0.9466030476383335, "recall": 0.9559921263868296 }, "clipping": { "support": 53342, "auc": 0.9996628084076009, "ap": 0.9958399399270511, "f1": 0.9745924813152567, "precision": 0.9701658895432, "recall": 0.9790596528064189 }, "lowpass": { "support": 103755, "auc": 0.9972200477300588, "ap": 0.9663775644557149, "f1": 0.8828647210322427, "precision": 0.7927302571025342, "recall": 0.9961254879282926 }, "highpass": { "support": 79278, "auc": 0.9951698279030602, "ap": 0.9914372288942742, "f1": 0.9781819105432932, "precision": 0.984886070122497, "recall": 0.9715684048538056 }, "codec": { "support": 83463, "auc": 0.9844503000683807, "ap": 0.9202691100421486, "f1": 0.8556850330055235, "precision": 0.804961505560308, "recall": 0.9132310125444808 }, "packet_loss": { "support": 8226, "auc": 0.9991369577014577, "ap": 0.9885315614558331, "f1": 0.9582109239163019, "precision": 0.9453448479829646, "recall": 0.9714320447362023 }, "hum": { "support": 86573, "auc": 0.9747932322282458, "ap": 0.7718321407856414, "f1": 0.727107298368753, "precision": 0.6409596502670591, "recall": 0.8400078546429025 }, "clicks": { "support": 8410, "auc": 0.9970920712414454, "ap": 0.9716312219485786, "f1": 0.9391625615763548, "precision": 0.9739463601532568, "recall": 0.9067776456599287 }, "pitch_shift": { "support": 63368, "auc": 0.9999093360621429, "ap": 0.9985917740639167, "f1": 0.9807648859838421, "precision": 0.9685187179763352, "recall": 0.993324706476455 }, "time_stretch": { "support": 69035, "auc": 0.9997985179311355, "ap": 0.9971987747664877, "f1": 0.9749158831714806, "precision": 0.9913158052344733, "recall": 0.9590497573694503 } }, "macro_auc": 0.9929812417391309, "macro_ap": 0.9547306796744809, "macro_f1": 0.9218349754503502 }, "segment_1s": { "per_class": { "noise": { "support": 1795, "auc": 0.9711004259498882, "ap": 0.8866178416157908, "f1": 0.876487252124646, "precision": 0.89164265129683, "recall": 0.8618384401114206 }, "music": { "support": 1904, "auc": 0.99813452489975, "ap": 0.9821528246280575, "f1": 0.9548755186721991, "precision": 0.9431352459016393, "recall": 0.9669117647058824 }, "reverb": { "support": 1783, "auc": 0.9944376847235489, "ap": 0.9839126735628216, "f1": 0.9413384742495181, "precision": 0.9247835497835498, "recall": 0.9584969153112731 }, "clipping": { "support": 1701, "auc": 0.9990176821176432, "ap": 0.9942784478123448, "f1": 0.9661164205039096, "precision": 0.952054794520548, "recall": 0.9805996472663139 }, "lowpass": { "support": 2347, "auc": 0.996268525655785, "ap": 0.9597394004075738, "f1": 0.8781402324709412, "precision": 0.7840642785403414, "recall": 0.9978696207925011 }, "highpass": { "support": 1780, "auc": 0.9956563198454678, "ap": 0.9925368559180535, "f1": 0.9734265734265733, "precision": 0.9693593314763231, "recall": 0.9775280898876404 }, "codec": { "support": 1860, "auc": 0.9821109314139737, "ap": 0.9194277426543178, "f1": 0.8442460317460317, "precision": 0.783609576427256, "recall": 0.9150537634408602 }, "packet_loss": { "support": 851, "auc": 0.9969630753304853, "ap": 0.9810067056159665, "f1": 0.9308390022675738, "precision": 0.8992332968236583, "recall": 0.9647473560517039 }, "hum": { "support": 1900, "auc": 0.974496713503215, "ap": 0.7996367102653053, "f1": 0.7360510134365748, "precision": 0.648735447611401, "recall": 0.8505263157894737 }, "clicks": { "support": 1009, "auc": 0.9895495994940707, "ap": 0.9668417250577295, "f1": 0.9308430085815244, "precision": 0.948559670781893, "recall": 0.9137760158572844 }, "pitch_shift": { "support": 1568, "auc": 0.9998322310602201, "ap": 0.9974695657503819, "f1": 0.9728549141965678, "precision": 0.952351863164325, "recall": 0.9942602040816326 }, "time_stretch": { "support": 1687, "auc": 0.9994617453027442, "ap": 0.9947724673904705, "f1": 0.9695704057279236, "precision": 0.975975975975976, "recall": 0.9632483698873741 } }, "macro_auc": 0.9914191216080659, "macro_ap": 0.9548660800565679, "macro_f1": 0.9145657372836652 }, "clip": { "per_class": { "noise": { "support": 367, "auc": 0.9612723026023713, "ap": 0.8973270908077903, "f1": 0.898186889818689, "precision": 0.92, "recall": 0.8773841961852861 }, "music": { "support": 377, "auc": 0.9962224597546091, "ap": 0.9782140352627451, "f1": 0.9513797634691196, "precision": 0.9427083333333334, "recall": 0.9602122015915119 }, "reverb": { "support": 358, "auc": 0.990459762580405, "ap": 0.9765173726916048, "f1": 0.9348127600554786, "precision": 0.928374655647383, "recall": 0.9413407821229051 }, "clipping": { "support": 349, "auc": 0.9960489581160378, "ap": 0.9914292731225425, "f1": 0.9645390070921985, "precision": 0.9550561797752809, "recall": 0.9742120343839542 }, "lowpass": { "support": 460, "auc": 0.9947881718589523, "ap": 0.963041972973026, "f1": 0.907114624505929, "precision": 0.8315217391304348, "recall": 0.9978260869565218 }, "highpass": { "support": 345, "auc": 0.9970059226507274, "ap": 0.9956927548894229, "f1": 0.9798850574712644, "precision": 0.9715099715099715, "recall": 0.9884057971014493 }, "codec": { "support": 358, "auc": 0.9729646577207888, "ap": 0.9201611173019183, "f1": 0.8412698412698414, "precision": 0.7989949748743719, "recall": 0.888268156424581 }, "packet_loss": { "support": 328, "auc": 0.9932594795165766, "ap": 0.9841272229654879, "f1": 0.9392592592592591, "precision": 0.9135446685878963, "recall": 0.9664634146341463 }, "hum": { "support": 348, "auc": 0.9701607765121965, "ap": 0.8548629199746827, "f1": 0.7806788511749346, "precision": 0.715311004784689, "recall": 0.8591954022988506 }, "clicks": { "support": 346, "auc": 0.9821068427632411, "ap": 0.9694729268045222, "f1": 0.9543446244477173, "precision": 0.972972972972973, "recall": 0.9364161849710982 }, "pitch_shift": { "support": 317, "auc": 0.9998265748473566, "ap": 0.9986047199260277, "f1": 0.9752321981424148, "precision": 0.9574468085106383, "recall": 0.9936908517350158 }, "time_stretch": { "support": 334, "auc": 0.9992773268167341, "ap": 0.9959707484069011, "f1": 0.973134328358209, "precision": 0.9702380952380952, "recall": 0.9760479041916168 } }, "macro_auc": 0.9877827696449996, "macro_ap": 0.9604518462605559, "macro_f1": 0.9249864337554211, "false_alarm_rate_on_clean_clips": 0.14527027027027026, "n_clean_clips": 592 }, "n_windows": 3000 }, "test_en_mit_rir": { "frame": { "per_class": { "noise": { "support": 27091, "auc": 0.9762173424230487, "ap": 0.8807451947330999, "f1": 0.8734767506572761, "precision": 0.9096650411703573, "recall": 0.8400575836993835 }, "music": { "support": 23749, "auc": 0.9989217227607523, "ap": 0.9792085617506755, "f1": 0.969319330678606, "precision": 0.9503196051460474, "recall": 0.989094277653796 }, "reverb": { "support": 25239, "auc": 0.9517186542857926, "ap": 0.8456230223549415, "f1": 0.7919675805392679, "precision": 0.9238854848933024, "recall": 0.69301477871548 }, "clipping": { "support": 17596, "auc": 0.9996346875075283, "ap": 0.9970022518461732, "f1": 0.9732722634508348, "precision": 0.9933136094674556, "recall": 0.9540236417367584 }, "lowpass": { "support": 29902, "auc": 0.9943997404425854, "ap": 0.9253195035948603, "f1": 0.808141839705822, "precision": 0.683429284872026, "recall": 0.988529195371547 }, "highpass": { "support": 28059, "auc": 0.999647168662574, "ap": 0.9964108961021396, "f1": 0.9753624980131046, "precision": 0.9667740354316925, "recall": 0.9841049217719805 }, "codec": { "support": 28632, "auc": 0.9797695927079737, "ap": 0.8707313470116367, "f1": 0.7976521363832543, "precision": 0.7886525791144642, "recall": 0.8068594579491478 }, "packet_loss": { "support": 2372, "auc": 0.9995229322867298, "ap": 0.9918031230962014, "f1": 0.9691629955947136, "precision": 0.964509394572025, "recall": 0.9738617200674536 }, "hum": { "support": 25147, "auc": 0.9829957470865325, "ap": 0.8257012439414378, "f1": 0.7206877810168486, "precision": 0.6150969918470621, "recall": 0.8700441404541297 }, "clicks": { "support": 2915, "auc": 0.9984451215209421, "ap": 0.9655776570931485, "f1": 0.9219858156028369, "precision": 0.9541284403669725, "recall": 0.8919382504288165 }, "pitch_shift": { "support": 24972, "auc": 0.9998428919064356, "ap": 0.9982855780946163, "f1": 0.9781812390508043, "precision": 0.9726049089469517, "recall": 0.9838218805061669 }, "time_stretch": { "support": 25199, "auc": 0.9998748850987682, "ap": 0.9983558341430309, "f1": 0.980218982517694, "precision": 0.9963925555464459, "recall": 0.9645620857970555 } }, "macro_auc": 0.9900825405574719, "macro_ap": 0.9395636844801635, "macro_f1": 0.896619101100922 }, "segment_1s": { "per_class": { "noise": { "support": 613, "auc": 0.9725175239514061, "ap": 0.8823288132785112, "f1": 0.8736401673640167, "precision": 0.8969072164948454, "recall": 0.8515497553017944 }, "music": { "support": 546, "auc": 0.9983796835487202, "ap": 0.9795164670035255, "f1": 0.9503546099290779, "precision": 0.9209621993127147, "recall": 0.9816849816849816 }, "reverb": { "support": 578, "auc": 0.9544013216109593, "ap": 0.8572873024976929, "f1": 0.8011417697431017, "precision": 0.8900634249471459, "recall": 0.7283737024221453 }, "clipping": { "support": 556, "auc": 0.9990006918473291, "ap": 0.9948328491470319, "f1": 0.9692028985507246, "precision": 0.9762773722627737, "recall": 0.9622302158273381 }, "lowpass": { "support": 686, "auc": 0.9926283592072713, "ap": 0.9140178367107324, "f1": 0.8056872037914693, "precision": 0.6786427145708582, "recall": 0.9912536443148688 }, "highpass": { "support": 619, "auc": 0.9996471751357403, "ap": 0.9965799300279332, "f1": 0.9553641346906812, "precision": 0.9270516717325228, "recall": 0.9854604200323102 }, "codec": { "support": 640, "auc": 0.9794826341711956, "ap": 0.8842349402626255, "f1": 0.8038490007401925, "precision": 0.7637130801687764, "recall": 0.8484375 }, "packet_loss": { "support": 264, "auc": 0.9993398422485272, "ap": 0.9847558011438253, "f1": 0.9239130434782609, "precision": 0.8854166666666666, "recall": 0.9659090909090909 }, "hum": { "support": 556, "auc": 0.9832676309248142, "ap": 0.8476698707710674, "f1": 0.730512249443207, "precision": 0.6219974715549936, "recall": 0.8848920863309353 }, "clicks": { "support": 356, "auc": 0.9948755530851453, "ap": 0.9724774143866611, "f1": 0.9321789321789322, "precision": 0.9584569732937686, "recall": 0.9073033707865169 }, "pitch_shift": { "support": 597, "auc": 0.9997101541748998, "ap": 0.9976891887340611, "f1": 0.9785831960461285, "precision": 0.9627228525121556, "recall": 0.9949748743718593 }, "time_stretch": { "support": 603, "auc": 0.9996322071316168, "ap": 0.9953264715724265, "f1": 0.9767441860465116, "precision": 0.978369384359401, "recall": 0.9751243781094527 } }, "macro_auc": 0.9894068980864689, "macro_ap": 0.9422264071280079, "macro_f1": 0.8917642826668587 }, "clip": { "per_class": { "noise": { "support": 124, "auc": 0.9686119089703933, "ap": 0.8998591966176134, "f1": 0.8806584362139918, "precision": 0.8991596638655462, "recall": 0.8629032258064516 }, "music": { "support": 114, "auc": 0.9977971169458635, "ap": 0.9843429612937049, "f1": 0.9606986899563318, "precision": 0.9565217391304348, "recall": 0.9649122807017544 }, "reverb": { "support": 121, "auc": 0.9604499854267152, "ap": 0.9032705541310309, "f1": 0.8444444444444444, "precision": 0.9134615384615384, "recall": 0.7851239669421488 }, "clipping": { "support": 112, "auc": 0.9988990106177607, "ap": 0.9946301217516003, "f1": 0.9683257918552036, "precision": 0.981651376146789, "recall": 0.9553571428571429 }, "lowpass": { "support": 145, "auc": 0.9882153660012098, "ap": 0.9135515716398611, "f1": 0.8640483383685801, "precision": 0.7688172043010753, "recall": 0.9862068965517241 }, "highpass": { "support": 118, "auc": 0.9992553518582574, "ap": 0.9954161978883156, "f1": 0.9243027888446216, "precision": 0.8721804511278195, "recall": 0.9830508474576272 }, "codec": { "support": 123, "auc": 0.9719757858924085, "ap": 0.9109254339034565, "f1": 0.8136882129277566, "precision": 0.7642857142857142, "recall": 0.8699186991869918 }, "packet_loss": { "support": 100, "auc": 0.9991777777777777, "ap": 0.994476221117894, "f1": 0.9519230769230769, "precision": 0.9166666666666666, "recall": 0.99 }, "hum": { "support": 106, "auc": 0.9820923557469081, "ap": 0.8810305301394162, "f1": 0.7685950413223139, "precision": 0.6838235294117647, "recall": 0.8773584905660378 }, "clicks": { "support": 122, "auc": 0.9886291497068598, "ap": 0.9800416309474747, "f1": 0.9586776859504132, "precision": 0.9666666666666667, "recall": 0.9508196721311475 }, "pitch_shift": { "support": 117, "auc": 0.9976914365362837, "ap": 0.9936060623589902, "f1": 0.983050847457627, "precision": 0.9747899159663865, "recall": 0.9914529914529915 }, "time_stretch": { "support": 121, "auc": 0.9990879944339454, "ap": 0.9959620833592652, "f1": 0.9833333333333334, "precision": 0.9915966386554622, "recall": 0.9752066115702479 } }, "macro_auc": 0.987656936659532, "macro_ap": 0.9539260470957185, "macro_f1": 0.9084788906331411, "false_alarm_rate_on_clean_clips": 0.14864864864864866, "n_clean_clips": 222 }, "n_windows": 1000 }, "test_en_real_rir": { "frame": { "per_class": { "noise": { "support": 24330, "auc": 0.985375380387137, "ap": 0.8874857361801259, "f1": 0.868822582012376, "precision": 0.8967976200892467, "recall": 0.8425400739827373 }, "music": { "support": 22023, "auc": 0.9992015163280261, "ap": 0.9832648899258126, "f1": 0.960227523259403, "precision": 0.9332333404756803, "recall": 0.98882985969214 }, "reverb": { "support": 27310, "auc": 0.9791884060160176, "ap": 0.9210360532135897, "f1": 0.8887186438014419, "precision": 0.9586388100182227, "recall": 0.8283046503112413 }, "clipping": { "support": 20978, "auc": 0.999562147710874, "ap": 0.9975167516789162, "f1": 0.9762022223788381, "precision": 0.9623882532771318, "recall": 0.9904185337019735 }, "lowpass": { "support": 40361, "auc": 0.9956537932994404, "ap": 0.9552235509514206, "f1": 0.857934680651488, "precision": 0.7528575437283697, "recall": 0.9971011620128342 }, "highpass": { "support": 20151, "auc": 0.9998537508807454, "ap": 0.9978010709585774, "f1": 0.9752632747182282, "precision": 0.9694057658364386, "recall": 0.9811920003970026 }, "codec": { "support": 25015, "auc": 0.988396873468717, "ap": 0.9176298609670425, "f1": 0.8526378896882494, "precision": 0.8524675324675325, "recall": 0.8528083150109934 }, "packet_loss": { "support": 3157, "auc": 0.9989400567205612, "ap": 0.9915215457352285, "f1": 0.9641622131405218, "precision": 0.9569422776911076, "recall": 0.9714919227114349 }, "hum": { "support": 26535, "auc": 0.9846001230266842, "ap": 0.7862753581481026, "f1": 0.7851138873323006, "precision": 0.6976771434429831, "recall": 0.8976069342377991 }, "clicks": { "support": 2587, "auc": 0.9992228126586093, "ap": 0.9852101080028043, "f1": 0.9604766633565045, "precision": 0.9877450980392157, "recall": 0.9346733668341709 }, "pitch_shift": { "support": 27914, "auc": 0.99961636190629, "ap": 0.9957944890414314, "f1": 0.9652028672837358, "precision": 0.9382991678506191, "recall": 0.9936949201117719 }, "time_stretch": { "support": 27908, "auc": 0.9993907723776294, "ap": 0.9934888998249539, "f1": 0.9613111131571678, "precision": 0.9888244876311703, "recall": 0.9352873727963308 } }, "macro_auc": 0.9940834995650608, "macro_ap": 0.9510206928856669, "macro_f1": 0.9180061300650212 }, "segment_1s": { "per_class": { "noise": { "support": 569, "auc": 0.9837713762159613, "ap": 0.8944177474876214, "f1": 0.875222816399287, "precision": 0.8878842676311031, "recall": 0.8629173989455184 }, "music": { "support": 504, "auc": 0.9991875296454404, "ap": 0.9861260616177089, "f1": 0.9529298751200769, "precision": 0.9236499068901304, "recall": 0.9841269841269841 }, "reverb": { "support": 611, "auc": 0.9799173983355185, "ap": 0.9255989629525935, "f1": 0.8786324786324786, "precision": 0.9194991055456172, "recall": 0.8412438625204582 }, "clipping": { "support": 650, "auc": 0.9992025934305346, "ap": 0.9953779073640093, "f1": 0.9609609609609611, "precision": 0.9384164222873901, "recall": 0.9846153846153847 }, "lowpass": { "support": 880, "auc": 0.9945571852655771, "ap": 0.9477433394346417, "f1": 0.8459681313375181, "precision": 0.7355163727959698, "recall": 0.9954545454545455 }, "highpass": { "support": 459, "auc": 0.9999396183940283, "ap": 0.9990306890769586, "f1": 0.9733191035218784, "precision": 0.9539748953974896, "recall": 0.9934640522875817 }, "codec": { "support": 555, "auc": 0.9823923184433594, "ap": 0.9128917841982765, "f1": 0.8380281690140845, "precision": 0.8192771084337349, "recall": 0.8576576576576577 }, "packet_loss": { "support": 312, "auc": 0.9963231113697397, "ap": 0.9817961447999888, "f1": 0.926605504587156, "precision": 0.8859649122807017, "recall": 0.9711538461538461 }, "hum": { "support": 592, "auc": 0.9831309103379838, "ap": 0.811450998903163, "f1": 0.7810650887573964, "precision": 0.6947368421052632, "recall": 0.8918918918918919 }, "clicks": { "support": 292, "auc": 0.9994819472385923, "ap": 0.9892621761486452, "f1": 0.9550173010380623, "precision": 0.965034965034965, "recall": 0.9452054794520548 }, "pitch_shift": { "support": 661, "auc": 0.9996374002567264, "ap": 0.996298854994608, "f1": 0.9611151870873075, "precision": 0.9330484330484331, "recall": 0.9909228441754917 }, "time_stretch": { "support": 679, "auc": 0.998992246767676, "ap": 0.991084587178196, "f1": 0.9548192771084337, "precision": 0.9768875192604006, "recall": 0.9337260677466863 } }, "macro_auc": 0.9930444696417616, "macro_ap": 0.9525899378463677, "macro_f1": 0.90864032446372 }, "clip": { "per_class": { "noise": { "support": 124, "auc": 0.972183863602887, "ap": 0.9033236001845246, "f1": 0.8934426229508197, "precision": 0.9083333333333333, "recall": 0.8790322580645161 }, "music": { "support": 102, "auc": 0.9978328747980261, "ap": 0.9848134369590466, "f1": 0.9473684210526315, "precision": 0.9252336448598131, "recall": 0.9705882352941176 }, "reverb": { "support": 119, "auc": 0.982954816432816, "ap": 0.9464112503272591, "f1": 0.8831168831168831, "precision": 0.9107142857142857, "recall": 0.8571428571428571 }, "clipping": { "support": 114, "auc": 0.9942279513682628, "ap": 0.9871795242797485, "f1": 0.9523809523809523, "precision": 0.9401709401709402, "recall": 0.9649122807017544 }, "lowpass": { "support": 159, "auc": 0.9921439735564879, "ap": 0.9427512643159155, "f1": 0.8681318681318682, "precision": 0.7707317073170732, "recall": 0.9937106918238994 }, "highpass": { "support": 90, "auc": 0.99997557997558, "ap": 0.9997584541062802, "f1": 0.972972972972973, "precision": 0.9473684210526315, "recall": 1.0 }, "codec": { "support": 104, "auc": 0.9661315247252747, "ap": 0.9051715964069142, "f1": 0.8169014084507041, "precision": 0.7981651376146789, "recall": 0.8365384615384616 }, "packet_loss": { "support": 126, "auc": 0.988562892739094, "ap": 0.9823675208411106, "f1": 0.9448818897637795, "precision": 0.9375, "recall": 0.9523809523809523 }, "hum": { "support": 113, "auc": 0.9748929971765222, "ap": 0.8456651771224659, "f1": 0.8016528925619835, "precision": 0.751937984496124, "recall": 0.8584070796460177 }, "clicks": { "support": 101, "auc": 0.9996695998854612, "ap": 0.9973576751073859, "f1": 0.99, "precision": 1.0, "recall": 0.9801980198019802 }, "pitch_shift": { "support": 127, "auc": 0.9994813792605821, "ap": 0.9965433185604732, "f1": 0.9652509652509653, "precision": 0.946969696969697, "recall": 0.984251968503937 }, "time_stretch": { "support": 128, "auc": 0.998709862385321, "ap": 0.9930289520341448, "f1": 0.9609375, "precision": 0.9609375, "recall": 0.9609375 } }, "macro_auc": 0.9888972763255262, "macro_ap": 0.9570309808537725, "macro_f1": 0.9164198647194634, "false_alarm_rate_on_clean_clips": 0.12935323383084577, "n_clean_clips": 201 }, "n_windows": 1000 }, "test_ru": { "frame": { "per_class": { "noise": { "support": 81329, "auc": 0.9604987261124202, "ap": 0.8025277031107889, "f1": 0.5618683718028696, "precision": 0.4113821788057162, "recall": 0.8859570386946846 }, "music": { "support": 80682, "auc": 0.9985034750549702, "ap": 0.9854590810432485, "f1": 0.9546264162030151, "precision": 0.9430074369671685, "recall": 0.966535286681044 }, "reverb": { "support": 85886, "auc": 0.9975715969387704, "ap": 0.9890707602861478, "f1": 0.9639349742989678, "precision": 0.9891444184422363, "recall": 0.9399785762522413 }, "clipping": { "support": 45997, "auc": 0.9995284939468562, "ap": 0.996160535403624, "f1": 0.9809907707218221, "precision": 0.9940849534608602, "recall": 0.9682370589386264 }, "lowpass": { "support": 111106, "auc": 0.9980785319290724, "ap": 0.9809664204069385, "f1": 0.8462654958084246, "precision": 0.7365228346876604, "recall": 0.9944377441362303 }, "highpass": { "support": 83549, "auc": 0.9995308571986256, "ap": 0.9975041507800847, "f1": 0.9891165907101681, "precision": 0.9977470894831701, "recall": 0.9806341189002861 }, "codec": { "support": 80596, "auc": 0.9903866937271524, "ap": 0.9493959330701672, "f1": 0.8593606228618615, "precision": 0.8190322000359777, "recall": 0.9038661968335897 }, "packet_loss": { "support": 8257, "auc": 0.9991328330939298, "ap": 0.9896103067689855, "f1": 0.9723499478879284, "precision": 0.9846039235162652, "recall": 0.960397238706552 }, "hum": { "support": 77260, "auc": 0.9700310117315668, "ap": 0.8643516822737889, "f1": 0.808859552219348, "precision": 0.8607058892247484, "recall": 0.7629044783846751 }, "clicks": { "support": 8383, "auc": 0.9974901436189798, "ap": 0.9751135933448568, "f1": 0.948892570096325, "precision": 0.9768822637695806, "recall": 0.9224621257306453 }, "pitch_shift": { "support": 72566, "auc": 0.999441627327891, "ap": 0.9921328301966863, "f1": 0.9513541590362729, "precision": 0.9204907153258334, "recall": 0.9843590662293636 }, "time_stretch": { "support": 70396, "auc": 0.9992112838509106, "ap": 0.991643830142524, "f1": 0.9565343127331617, "precision": 0.9739693757361602, "recall": 0.9397124836638445 } }, "macro_auc": 0.9924504395442622, "macro_ap": 0.9594947355689866, "macro_f1": 0.8995128153650137 }, "segment_1s": { "per_class": { "noise": { "support": 1826, "auc": 0.9588785416270065, "ap": 0.8118856763812923, "f1": 0.5483116014710799, "precision": 0.3946102021174206, "recall": 0.8981380065717415 }, "music": { "support": 1838, "auc": 0.9979314453594704, "ap": 0.9842554962249991, "f1": 0.9466382070437568, "precision": 0.9287958115183246, "recall": 0.9651795429815017 }, "reverb": { "support": 1938, "auc": 0.9965777091841466, "ap": 0.9869481133356713, "f1": 0.9584313725490198, "precision": 0.9713831478537361, "recall": 0.9458204334365325 }, "clipping": { "support": 1581, "auc": 0.9990370634324373, "ap": 0.9931273281736334, "f1": 0.9778200253485425, "precision": 0.9796825396825397, "recall": 0.9759645793801391 }, "lowpass": { "support": 2495, "auc": 0.9972973149274601, "ap": 0.9772449244467835, "f1": 0.8025210084033614, "precision": 0.6723531004603304, "recall": 0.995190380761523 }, "highpass": { "support": 1879, "auc": 0.9996662846097396, "ap": 0.9978072300464331, "f1": 0.9874230666309874, "precision": 0.9930032292787944, "recall": 0.9819052687599787 }, "codec": { "support": 1816, "auc": 0.9865570281434729, "ap": 0.9429442150035149, "f1": 0.8288016112789527, "precision": 0.7634508348794063, "recall": 0.9063876651982379 }, "packet_loss": { "support": 872, "auc": 0.9975980890461252, "ap": 0.9839538081721221, "f1": 0.9534215066129961, "precision": 0.9561707035755479, "recall": 0.9506880733944955 }, "hum": { "support": 1735, "auc": 0.967002344693957, "ap": 0.8588409405361159, "f1": 0.7922962962962962, "precision": 0.8152439024390243, "recall": 0.7706051873198847 }, "clicks": { "support": 982, "auc": 0.9935183007375724, "ap": 0.9668101783472817, "f1": 0.9295336787564766, "precision": 0.9462025316455697, "recall": 0.9134419551934827 }, "pitch_shift": { "support": 1748, "auc": 0.999050617322421, "ap": 0.9902967087244904, "f1": 0.9265141318977119, "precision": 0.874936451448907, "recall": 0.9845537757437071 }, "time_stretch": { "support": 1710, "auc": 0.9983450389474368, "ap": 0.9868860344179521, "f1": 0.9496946786856645, "precision": 0.9444765760555234, "recall": 0.9549707602339181 } }, "macro_auc": 0.9909549815026036, "macro_ap": 0.9567500544841908, "macro_f1": 0.8834505987479039 }, "clip": { "per_class": { "noise": { "support": 358, "auc": 0.9529680621164769, "ap": 0.8369869489774066, "f1": 0.6013071895424836, "precision": 0.45161290322580644, "recall": 0.8994413407821229 }, "music": { "support": 369, "auc": 0.995261315212924, "ap": 0.9817835501318576, "f1": 0.9503355704697988, "precision": 0.9414893617021277, "recall": 0.959349593495935 }, "reverb": { "support": 383, "auc": 0.9873681921080383, "ap": 0.9763234791904579, "f1": 0.949868073878628, "precision": 0.96, "recall": 0.9399477806788512 }, "clipping": { "support": 331, "auc": 0.9964021285001002, "ap": 0.9920111759404076, "f1": 0.9802130898021308, "precision": 0.9877300613496932, "recall": 0.972809667673716 }, "lowpass": { "support": 474, "auc": 0.9939364783467133, "ap": 0.9724250775619331, "f1": 0.8156521739130436, "precision": 0.6937869822485208, "recall": 0.989451476793249 }, "highpass": { "support": 365, "auc": 0.99965116581321, "ap": 0.9985539176738065, "f1": 0.9931412894375857, "precision": 0.9945054945054945, "recall": 0.9917808219178083 }, "codec": { "support": 351, "auc": 0.9704048939609529, "ap": 0.9252290019010437, "f1": 0.8072445019404916, "precision": 0.7393364928909952, "recall": 0.8888888888888888 }, "packet_loss": { "support": 329, "auc": 0.9959050206029184, "ap": 0.9901403382160633, "f1": 0.9679389312977099, "precision": 0.9723926380368099, "recall": 0.9635258358662614 }, "hum": { "support": 350, "auc": 0.952677628032345, "ap": 0.857516983844412, "f1": 0.7904903417533432, "precision": 0.8235294117647058, "recall": 0.76 }, "clicks": { "support": 333, "auc": 0.9925251460684531, "ap": 0.9816671501584321, "f1": 0.9586523736600306, "precision": 0.978125, "recall": 0.93993993993994 }, "pitch_shift": { "support": 348, "auc": 0.9980311974480331, "ap": 0.9896868976831013, "f1": 0.9193548387096775, "precision": 0.8636363636363636, "recall": 0.9827586206896551 }, "time_stretch": { "support": 343, "auc": 0.9946189777593922, "ap": 0.983387683415535, "f1": 0.9416785206258891, "precision": 0.9194444444444444, "recall": 0.9650145772594753 } }, "macro_auc": 0.9858125171641299, "macro_ap": 0.957142683724538, "macro_f1": 0.8896564079192344, "false_alarm_rate_on_clean_clips": 0.33220910623946037, "n_clean_clips": 593 }, "n_windows": 3000 } }, "ood": { "VoiceBank-DEMAND test (824 noisy vs 824 clean twins)": { "n": 1648, "noise": { "auc_mean": 0.9891233268922612, "auc_p95": 0.9854766589688, "recall_at_0.5_p95": 0.5060679611650486, "false_alarm_at_0.5_p95": 0.0036407766990291263 }, "clean_clips_any_class_false_alarm": 0.0036407766990291263, "clean_clips_false_alarm_by_class": { "noise": 0.0036407766990291263, "music": 0.0, "reverb": 0.0, "clipping": 0.0, "lowpass": 0.0, "highpass": 0.0, "codec": 0.0, "packet_loss": 0.0, "hum": 0.0, "clicks": 0.0, "pitch_shift": 0.0, "time_stretch": 0.0 } }, "DNS-2020 synthetic (clean / noisy, dry / reverberant)": { "n": 600, "noise": { "auc_mean": 0.9989111111111111, "auc_p95": 0.9973333333333333, "recall_at_0.5_p95": 0.8533333333333334, "false_alarm_at_0.5_p95": 0.0 }, "reverb": { "auc_mean": 1.0, "auc_p95": 1.0, "recall_at_0.5_p95": 1.0, "false_alarm_at_0.5_p95": 0.0 }, "clean_clips_any_class_false_alarm": 0.006666666666666667, "clean_clips_false_alarm_by_class": { "noise": 0.0, "music": 0.0, "reverb": 0.0, "clipping": 0.0, "lowpass": 0.0, "highpass": 0.0, "codec": 0.006666666666666667, "packet_loss": 0.0, "hum": 0.0, "clicks": 0.0, "pitch_shift": 0.0, "time_stretch": 0.0 } }, "Dynamic-SUPERB NoiseDetection_VCTK_MUSAN-Noise": { "n": 200, "noise": { "auc_mean": 0.9961689686460329, "auc_p95": 0.994959169271096, "recall_at_0.5_p95": 0.963302752293578, "false_alarm_at_0.5_p95": 0.01098901098901099 }, "clean_clips_any_class_false_alarm": 0.03296703296703297, "clean_clips_false_alarm_by_class": { "noise": 0.01098901098901099, "music": 0.0, "reverb": 0.0, "clipping": 0.0, "lowpass": 0.0, "highpass": 0.0, "codec": 0.0, "packet_loss": 0.0, "hum": 0.0, "clicks": 0.0, "pitch_shift": 0.0, "time_stretch": 0.02197802197802198 } }, "Dynamic-SUPERB ReverberationDetection_VCTK_RirsNoises-SmallRoom": { "n": 200, "reverb": { "auc_mean": 0.9962761674718197, "auc_p95": 0.9948671497584541, "recall_at_0.5_p95": 0.967391304347826, "false_alarm_at_0.5_p95": 0.0 }, "clean_clips_any_class_false_alarm": 0.06481481481481481, "clean_clips_false_alarm_by_class": { "noise": 0.018518518518518517, "music": 0.0, "reverb": 0.0, "clipping": 0.0, "lowpass": 0.0, "highpass": 0.0, "codec": 0.0, "packet_loss": 0.0, "hum": 0.0, "clicks": 0.0, "pitch_shift": 0.0, "time_stretch": 0.046296296296296294 } }, "Dynamic-SUPERB ReverberationDetection_VCTK_RirsNoises-MediumRoom": { "n": 200, "reverb": { "auc_mean": 1.0, "auc_p95": 1.0, "recall_at_0.5_p95": 1.0, "false_alarm_at_0.5_p95": 0.0 }, "clean_clips_any_class_false_alarm": 0.06481481481481481, "clean_clips_false_alarm_by_class": { "noise": 0.018518518518518517, "music": 0.0, "reverb": 0.0, "clipping": 0.0, "lowpass": 0.0, "highpass": 0.0, "codec": 0.0, "packet_loss": 0.0, "hum": 0.0, "clicks": 0.0, "pitch_shift": 0.0, "time_stretch": 0.046296296296296294 } }, "Dynamic-SUPERB ReverberationDetection_VCTK_RirsNoises-LargeRoom": { "n": 200, "reverb": { "auc_mean": 0.9980877616747181, "auc_p95": 0.9976348631239936, "recall_at_0.5_p95": 0.9565217391304348, "false_alarm_at_0.5_p95": 0.0 }, "clean_clips_any_class_false_alarm": 0.05555555555555555, "clean_clips_false_alarm_by_class": { "noise": 0.018518518518518517, "music": 0.0, "reverb": 0.0, "clipping": 0.0, "lowpass": 0.0, "highpass": 0.0, "codec": 0.0, "packet_loss": 0.0, "hum": 0.0, "clicks": 0.0, "pitch_shift": 0.0, "time_stretch": 0.037037037037037035 } } } }