{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/easycom","name":"EasyCom","full_name":null,"description_markdown":"The Easy Communications (EasyCom) dataset is a world-first dataset designed to help mitigate the cocktail party effect from an augmented-reality (AR) -motivated multi-sensor egocentric world view. The dataset contains AR glasses egocentric multi-channel microphone array audio, wide field-of-view RGB video, speech source pose, headset microphone audio, annotated voice activity, speech transcriptions, head and face bounding boxes and source identification labels. We have created and are releasing this dataset to facilitate research in multi-modal AR solutions to the cocktail party problem.\r\n\r\nSource: [EasyCom](https://github.com/facebookresearch/EasyComDataset)","description_withheld":null,"homepage":"https://github.com/facebookresearch/EasyComDataset","introduced_date":"2021-07-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/easycom-an-augmented-reality-dataset-to","title":"EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments","first_author":"Jacob Donley","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Time series","url":"/datasets/modality/time-series"},{"name":"Speech","url":"/datasets/modality/speech"},{"name":"Dialog","url":"/datasets/modality/dialog"},{"name":"RGB Video","url":"/datasets/modality/rgb-video"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Speech Enhancement","url":"/task/speech-enhancement","datasets_with_task":"/datasets/task/speech-enhancement"},{"name":"Face Clustering","url":"/task/face-clustering","datasets_with_task":"/datasets/task/face-clustering"},{"name":"Active Speaker Localization","url":"/task/active-speaker-localization","datasets_with_task":"/datasets/task/active-speaker-localization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["EasyCom"],"data_loaders":[],"num_papers_in_archive":22,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-enhancement-on-easycom","task":"Speech Enhancement","dataset_variant":"EasyCom","rows":6,"metrics":["PESQ","STOI","ViSQOL","HASQI","Audio Quality MOS","SDR","ESTOI","HASPI","SI-SDR","SIIB","SNR","SegSNR"],"first_row_in_archive_order":{"model":"MaxDI (Baseline)","paper":"/paper/easycom-an-augmented-reality-dataset-to","metrics":{"ESTOI":"0.379","HASPI":"0.830","HASQI":"0.249","PESQ":"1.17","SDR":"-12.9","SI-SDR":"-23.4","SIIB":"139","SNR":"-10.1","STOI":"0.544","SegSNR":"-12.2","ViSQOL":"1.68"},"code_links":[{"title":"facebookresearch/EasyComDataset","url":"https://github.com/facebookresearch/EasyComDataset"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-easycom","task":"Speech Recognition","dataset_variant":"EasyCom","rows":5,"metrics":["WER (%)"],"first_row_in_archive_order":{"model":"ReVISE (bf)","paper":"/paper/revise-self-supervised-speech-resynthesis","metrics":{"WER (%)":"52.1"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/active-speaker-localization-on-easycom","task":"Active Speaker Localization","dataset_variant":"EasyCom","rows":1,"metrics":["ASL mAP"],"first_row_in_archive_order":{"model":"AV (cor+eng+box)","paper":"/paper/egocentric-deep-multi-channel-audio-visual","metrics":{"ASL mAP":"0.8632"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/face-clustering-on-easycom","task":"Face Clustering","dataset_variant":"EasyCom","rows":1,"metrics":["NMI"],"first_row_in_archive_order":{"model":"VC TRSF.","paper":"/paper/self-supervised-video-centralised-transformer","metrics":{"NMI":"87.44"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":5,"of":5,"counts":{"papers_with_a_benchmark_row":5,"with_a_code_link":1,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":5,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/revise-self-supervised-speech-resynthesis","slug":"revise-self-supervised-speech-resynthesis","title":"ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement","date":"2022-12-21","arxiv_id":"2212.11377","rows_on_this_dataset":8,"code_links":0,"syntology":null},{"paper":"/paper/direction-aware-joint-adaptation-of-neural","slug":"direction-aware-joint-adaptation-of-neural","title":"Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments","date":"2022-07-15","arxiv_id":"2207.07273","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/self-supervised-video-centralised-transformer","slug":"self-supervised-video-centralised-transformer","title":"Self-supervised Video-centralised Transformer for Video Face Clustering","date":"2022-03-24","arxiv_id":"2203.13166","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/egocentric-deep-multi-channel-audio-visual","slug":"egocentric-deep-multi-channel-audio-visual","title":"Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization","date":"2022-01-06","arxiv_id":"2201.01928","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/easycom-an-augmented-reality-dataset-to","slug":"easycom-an-augmented-reality-dataset-to","title":"EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments","date":"2021-07-09","arxiv_id":"2107.04174","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/revise-self-supervised-speech-resynthesis","slug":"revise-self-supervised-speech-resynthesis","title":"ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement","date":"2022-12-21","arxiv_id":"2212.11377","rows_on_this_dataset":8,"code_links":0,"syntology":null},{"paper":"/paper/direction-aware-joint-adaptation-of-neural","slug":"direction-aware-joint-adaptation-of-neural","title":"Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments","date":"2022-07-15","arxiv_id":"2207.07273","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/self-supervised-video-centralised-transformer","slug":"self-supervised-video-centralised-transformer","title":"Self-supervised Video-centralised Transformer for Video Face Clustering","date":"2022-03-24","arxiv_id":"2203.13166","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/egocentric-deep-multi-channel-audio-visual","slug":"egocentric-deep-multi-channel-audio-visual","title":"Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization","date":"2022-01-06","arxiv_id":"2201.01928","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/easycom-an-augmented-reality-dataset-to","slug":"easycom-an-augmented-reality-dataset-to","title":"EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments","date":"2021-07-09","arxiv_id":"2107.04174","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":0,"papers_with_a_run_with_no_instrument_failure":0,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"5264eab706c3ac5c1bf93d6fea06bcb6ecda7013caf09ad28c08e1f3d6e081a9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}