FunASR/docs/m2met2/_build/html/searchindex.js

Search.setIndex({"docnames": ["Baseline", "Contact", "Dataset", "Introduction", "Organizers", "Rules", "Track_setting_and_evaluation", "index"], "filenames": ["Baseline.md", "Contact.md", "Dataset.md", "Introduction.md", "Organizers.md", "Rules.md", "Track_setting_and_evaluation.md", "index.rst"], "titles": ["Baseline", "Contact", "Datasets", "Introduction", "Organizers", "Rules", "Track & Evaluation", "ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)"], "terms": {"we": [0, 2, 3, 7], "releas": [0, 2, 3, 6], "an": [0, 2, 3, 6], "e2": 0, "sa": 0, "asr": [0, 3, 7], "conduct": [0, 2], "funasr": 0, "time": [0, 6], "accord": [0, 3], "timelin": [0, 2], "The": [0, 2, 3, 5, 6], "model": [0, 2, 3, 5, 6], "architectur": 0, "i": [0, 2, 3, 5], "shown": [0, 2], "figur": [0, 6], "3": [0, 2, 3], "speakerencod": 0, "initi": 0, "pre": [0, 6], "train": [0, 3, 5, 7], "speaker": [0, 2, 3, 7], "verif": 0, "from": [0, 2, 3, 5, 6], "modelscop": [0, 6], "thi": [0, 3, 5, 6], "also": [0, 2, 3, 6], "us": [0, 2, 5, 6], "extract": 0, "embed": 0, "profil": 0, "To": [0, 2, 3, 7], "run": 0, "first": 0, "you": [0, 1], "need": 0, "instal": 0, "There": [0, 2], "ar": [0, 2, 3, 5, 6, 7], "two": [0, 3, 5, 7], "startup": 0, "script": [0, 2], "sh": 0, "evalu": [0, 2, 3, 7], "old": 0, "eval": [0, 2, 5, 6], "test": [0, 2, 3, 5, 6], "set": [0, 2, 3, 5, 6], "run_m2met_2023_inf": 0, "infer": 0, "new": [0, 2, 3, 6], "multi": [0, 3, 6], "channel": [0, 3], "parti": [0, 3, 6], "meet": [0, 2, 3, 6], "transcript": [0, 2, 3, 5, 6], "2": [0, 2, 6], "0": [0, 1, 2, 3], "m2met2": [0, 1, 3], "challeng": [0, 1, 3, 5, 6], "befor": 0, "must": [0, 3, 5, 6], "manual": [0, 6], "download": [0, 2], "unpack": 0, "alimeet": [0, 1, 6], "corpu": [0, 6], "place": [0, 2], "dataset": [0, 3, 5, 6, 7], "directori": 0, "eval_ali_far": 0, "eval_ali_near": 0, "test_ali_far": 0, "test_ali_near": 0, "train_ali_far": 0, "train_ali_near": 0, "test_2023_ali_far": 0, "after": 0, "which": [0, 2, 3, 6], "contain": [0, 2, 6], "onli": [0, 2, 5, 6], "raw": 0, "audio": [0, 2, 3, 6], "Then": 0, "put": 0, "given": 0, "wav": 0, "scp": 0, "wav_raw": 0, "segment": [0, 2, 6], "utt2spk": 0, "spk2utt": 0, "data": [0, 3, 5, 6], "For": [0, 2], "more": [0, 2], "detail": [0, 3, 6], "can": [0, 2, 3, 5, 6], "see": 0, "here": 0, "system": [0, 3, 5, 6, 7], "tabl": [0, 2], "adopt": 0, "oracl": [0, 6], "dure": [0, 2, 6], "howev": [0, 3, 6], "due": [0, 3], "lack": 0, "label": [0, 5, 6], "provid": [0, 2, 6, 7], "addit": [0, 6], "spectral": 0, "cluster": 0, "meanwhil": 0, "show": 0, "impact": 0, "accuraci": [0, 6], "If": [1, 5, 6], "have": [1, 3], "ani": [1, 5, 6], "question": 1, "about": [1, 3], "pleas": 1, "u": [1, 2], "email": [1, 3, 4], "m2met": [1, 3, 6, 7], "gmail": 1, "com": [1, 4], "wechat": [1, 3], "group": [1, 2, 3], "In": [2, 3, 5], "fix": [2, 3, 7], "condit": [2, 3, 7], "restrict": 2, "three": [2, 3, 6], "publicli": [2, 6], "avail": [2, 6], "corpora": 2, "name": 2, "aishel": [2, 4, 6], "4": [2, 6], "cn": [2, 4, 6], "celeb": [2, 6], "perform": [2, 3], "call": 2, "2023": [2, 3, 5, 6], "score": [2, 6], "rank": [2, 3, 6], "describ": 2, "118": 2, "75": 2, "hour": [2, 3, 6], "speech": [2, 3, 6, 7], "total": [2, 6], "divid": [2, 6], "104": 2, "10": [2, 3, 6], "specif": [2, 6], "212": 2, "8": 2, "20": [2, 3], "session": [2, 3, 6, 7], "respect": 2, "each": [2, 3, 6], "consist": [2, 6], "15": 2, "30": 2, "minut": 2, "discuss": 2, "particip": [2, 5, 6], "number": [2, 3, 6], "456": 2, "25": 2, "60": 2, "balanc": 2, "gender": 2, "coverag": 2, "collect": 2, "13": 2, "venu": 2, "categor": 2, "type": 2, "small": 2, "medium": 2, "larg": [2, 3], "room": [2, 3], "size": 2, "rang": 2, "m": 2, "55": 2, "differ": [2, 3, 6], "give": 2, "varieti": 2, "acoust": [2, 3, 6], "properti": 2, "layout": 2, "paramet": [2, 5], "togeth": 2, "wall": 2, "materi": 2, "cover": 2, "cement": 2, "glass": 2, "etc": 2, "other": 2, "furnish": 2, "includ": [2, 3, 5, 6], "sofa": 2, "tv": 2, "blackboard": 2, "fan": 2, "air": 2, "condition": 2, "plant": 2, "record": [2, 6], "sit": 2, "around": 2, "microphon": [2, 3], "arrai": [2, 3], "natur": 2, "convers": 2, "distanc": 2, "5": 2, "all": [2, 3, 5, 6], "nativ": 2, "chines": 2, "speak": [2, 3], "mandarin": [2, 3], "without": 2, "strong": 2, "accent": 2, "variou": [2, 3], "kind": 2, "indoor": 2, "nois": [2, 3, 5], "limit": [2, 3, 5], "click": 2, "keyboard": 2, "door": 2, "open": [2, 3, 7], "close": [2, 3], "bubbl": 2, "made": [2, 3], "both": [2, 6], "requir": [2, 3, 6], "remain": [2, 3], "same": [2, 5], "posit": 2, "overlap": [2, 3], "between": [2, 6], "exampl": 2, "fig": 2, "1": 2, "within": [2, 3], "one": [2, 5], "ensur": 2, "ratio": 2, "select": [2, 3, 5, 6], "topic": 2, "medic": 2, "treatment": 2, "educ": 2, "busi": 2, "organ": [2, 3, 5, 6, 7], "manag": 2, "industri": [2, 3], "product": 2, "daili": 2, "routin": 2, "averag": 2, "42": 2, "27": 2, "34": 2, "76": 2, "A": [2, 4], "distribut": 2, "were": 2, "ident": [2, 6], "compris": [2, 3, 7], "therebi": 2, "share": 2, "similar": 2, "configur": 2, "field": [2, 3, 6], "signal": [2, 3], "headset": 2, "": [2, 6], "own": 2, "transcrib": [2, 3, 6], "It": [2, 6], "worth": [2, 6], "note": [2, 6], "far": [2, 3], "synchron": 2, "common": 2, "prepar": 2, "textgrid": 2, "format": 2, "inform": [2, 3], "durat": 2, "id": 2, "timestamp": [2, 6], "mention": 2, "abov": 2, "openslr": 2, "via": 2, "follow": [2, 5], "link": 2, "particularli": 2, "baselin": [2, 3, 7], "conveni": 2, "automat": [3, 7], "recognit": [3, 7], "diariz": 3, "signific": 3, "stride": 3, "recent": 3, "year": 3, "result": 3, "surg": 3, "technologi": 3, "applic": 3, "across": 3, "domain": 3, "present": 3, "uniqu": [3, 6], "complex": [3, 5], "divers": 3, "style": 3, "variabl": 3, "confer": 3, "environment": 3, "reverber": [3, 5], "over": 3, "sever": 3, "been": 3, "advanc": [3, 7], "develop": [3, 6], "rich": 3, "comput": [3, 5], "hear": 3, "multisourc": 3, "environ": 3, "chime": 3, "latest": 3, "iter": 3, "ha": 3, "particular": 3, "focu": 3, "distant": 3, "gener": 3, "topologi": 3, "scenario": 3, "while": 3, "progress": 3, "english": 3, "languag": [3, 5], "barrier": 3, "achiev": 3, "compar": 3, "non": 3, "multimod": 3, "base": 3, "process": [3, 6], "misp": 3, "instrument": 3, "seek": 3, "address": 3, "problem": 3, "visual": 3, "everydai": 3, "home": 3, "focus": 3, "tackl": 3, "issu": 3, "offlin": 3, "icassp2022": 3, "main": 3, "task": [3, 6, 7], "former": 3, "involv": [3, 6], "identifi": 3, "who": 3, "spoke": 3, "when": 3, "latter": 3, "aim": 3, "multipl": [3, 6], "simultan": 3, "pose": [3, 6], "technic": 3, "difficulti": 3, "interfer": 3, "build": [3, 6, 7], "success": [3, 7], "previou": 3, "excit": 3, "propos": [3, 7], "asru": 3, "special": [3, 5, 7], "origin": [3, 5], "metric": [3, 7], "wa": [3, 6], "independ": 3, "meant": 3, "could": 3, "determin": 3, "correspond": [3, 5], "further": 3, "current": [3, 7], "talker": [3, 7], "toward": 3, "practic": 3, "attribut": [3, 7], "sub": [3, 5, 7], "track": [3, 5, 7], "what": 3, "facilit": [3, 7], "reproduc": [3, 7], "research": [3, 4, 7], "offer": 3, "comprehens": [3, 7], "overview": [3, 7], "rule": [3, 7], "furthermor": 3, "carefulli": 3, "curat": 3, "approxim": [3, 6], "design": 3, "enabl": 3, "valid": 3, "state": [3, 6, 7], "art": [3, 7], "area": 3, "april": 3, "29": 3, "registr": 3, "mai": 3, "11": 3, "22": 3, "deadlin": 3, "date": 3, "join": 3, "june": 3, "16": 3, "leaderboard": 3, "final": [3, 5, 6], "submiss": 3, "leaderboar": 3, "26": 3, "juli": 3, "paper": [3, 6], "decemb": 3, "12": 3, "workshop": 3, "interest": 3, "whether": 3, "academia": 3, "regist": 3, "complet": 3, "googl": 3, "form": 3, "below": 3, "welcom": 3, "keep": 3, "up": 3, "updat": 3, "work": 3, "dai": 3, "send": 3, "invit": 3, "elig": [3, 5], "team": 3, "qualifi": 3, "adher": [3, 5], "publish": 3, "page": 3, "prior": 3, "submit": 3, "descript": [3, 6], "document": 3, "approach": [3, 5], "method": 3, "top": 3, "asru2023": [3, 7], "proceed": 3, "lei": 4, "xie": 4, "professor": 4, "foundat": 4, "china": 4, "lxie": 4, "nwpu": 4, "edu": 4, "kong": 4, "aik": 4, "lee": 4, "senior": 4, "scientist": 4, "institut": 4, "infocomm": 4, "star": 4, "singapor": 4, "kongaik": 4, "ieee": 4, "org": 4, "zhiji": 4, "yan": 4, "princip": 4, "engin": 4, "alibaba": 4, "yzj": 4, "inc": 4, "shiliang": 4, "zhang": 4, "sly": 4, "zsl": 4, "yanmin": 4, "qian": 4, "shanghai": 4, "jiao": 4, "tong": 4, "univers": 4, "yanminqian": 4, "sjtu": 4, "zhuo": 4, "chen": 4, "appli": 4, "microsoft": 4, "usa": 4, "zhuc": 4, "jian": 4, "wu": 4, "wujian": 4, "hui": 4, "bu": 4, "ceo": 4, "buhui": 4, "aishelldata": 4, "should": 5, "augment": 5, "allow": [5, 6], "ad": 5, "speed": 5, "perturb": 5, "tone": 5, "chang": 5, "permit": 5, "purpos": 5, "instead": [5, 6], "util": [5, 6], "tune": 5, "violat": 5, "strictli": [5, 6], "prohibit": [5, 6], "fine": 5, "cpcer": [5, 6], "lower": 5, "judg": 5, "superior": 5, "forc": 5, "align": 5, "obtain": [5, 6], "frame": 5, "level": 5, "classif": 5, "basi": 5, "shallow": 5, "fusion": 5, "end": 5, "e": [5, 6], "g": 5, "la": 5, "rnnt": 5, "transform": [5, 6], "come": 5, "right": 5, "interpret": 5, "belong": 5, "case": 5, "circumst": 5, "coordin": 5, "assign": 6, "illustr": 6, "aishell4": 6, "constrain": 6, "sourc": 6, "addition": 6, "soon": 6, "simpl": 6, "voic": 6, "activ": 6, "detect": 6, "vad": 6, "concaten": 6, "minimum": 6, "permut": 6, "charact": 6, "error": 6, "rate": 6, "calcul": 6, "step": 6, "firstli": 6, "refer": 6, "hypothesi": 6, "chronolog": 6, "order": 6, "secondli": 6, "cer": 6, "repeat": 6, "possibl": 6, "lowest": 6, "tthe": 6, "insert": 6, "Ins": 6, "substitut": 6, "delet": 6, "del": 6, "output": 6, "text": 6, "frac": 6, "mathcal": 6, "n_": 6, "100": 6, "where": 6, "usag": 6, "third": 6, "hug": 6, "face": 6, "list": 6, "clearli": 6, "privat": 6, "simul": 6, "thei": 6, "mandatori": 6, "clear": 6, "scheme": 6, "delight": 7, "introduct": 7, "contact": 7}, "objects": {}, "objtypes": {}, "objnames": {}, "titleterms": {"baselin": 0, "overview": [0, 2], "quick": 0, "start": 0, "result": 0, "contact": 1, "dataset": 2, "train": [2, 6], "data": 2, "detail": 2, "alimeet": 2, "corpu": 2, "get": 2, "introduct": 3, "call": 3, "particip": 3, "timelin": 3, "aoe": 3, "time": 3, "guidelin": 3, "organ": 4, "rule": 5, "track": 6, "evalu": 6, "speaker": 6, "attribut": 6, "asr": 6, "metric": 6, "sub": 6, "arrang": 6, "i": 6, "fix": 6, "condit": 6, "ii": 6, "open": 6, "asru": 7, "2023": 7, "multi": 7, "channel": 7, "parti": 7, "meet": 7, "transcript": 7, "challeng": 7, "2": 7, "0": 7, "m2met2": 7, "content": 7}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 57}, "alltitles": {"Baseline": [[0, "baseline"]], "Overview": [[0, "overview"]], "Quick start": [[0, "quick-start"]], "Baseline results": [[0, "baseline-results"]], "Contact": [[1, "contact"]], "Datasets": [[2, "datasets"]], "Overview of training data": [[2, "overview-of-training-data"]], "Detail of AliMeeting corpus": [[2, "detail-of-alimeeting-corpus"]], "Get the data": [[2, "get-the-data"]], "Introduction": [[3, "introduction"]], "Call for participation": [[3, "call-for-participation"]], "Timeline(AOE Time)": [[3, "timeline-aoe-time"]], "Guidelines": [[3, "guidelines"]], "Organizers": [[4, "organizers"]], "Rules": [[5, "rules"]], "Track & Evaluation": [[6, "track-evaluation"]], "Speaker-Attributed ASR": [[6, "speaker-attributed-asr"]], "Evaluation metric": [[6, "evaluation-metric"]], "Sub-track arrangement": [[6, "sub-track-arrangement"]], "Sub-track I (Fixed Training Condition):": [[6, "sub-track-i-fixed-training-condition"]], "Sub-track II (Open Training Condition):": [[6, "sub-track-ii-open-training-condition"]], "ASRU 2023 MULTI-CHANNEL MULTI-PARTY MEETING TRANSCRIPTION CHALLENGE 2.0 (M2MeT2.0)": [[7, "asru-2023-multi-channel-multi-party-meeting-transcription-challenge-2-0-m2met2-0"]], "Contents:": [[7, null]]}, "indexentries": {}})