{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LDOADVJCCED62FCBR6CCSEOH44","short_pith_number":"pith:LDOADVJC","schema_version":"1.0","canonical_sha256":"58dc01d5221107ed14418f842911c7e704b2448cdb10d7a7ab8e4cbf2304fb4b","source":{"kind":"arxiv","id":"2303.01812","version":1},"attestation_state":"computed","paper":{"title":"Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heinrich Dinkel, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","submitted_at":"2023-03-03T09:38:53Z","abstract_excerpt":"Keyword spotting (KWS) is a core human-machine-interaction front-end task for most modern intelligent assistants. Recently, a unified (UniKW-AT) framework has been proposed that adds additional capabilities in the form of audio tagging (AT) to a KWS model. However, previous work did not consider the real-world deployment of a UniKW-AT model, where factors such as model size and inference speed are more important than performance alone. This work introduces three mobile-device deployable models named Unified Transformers (UiT). Our best model achieves an mAP of 34.09 on Audioset, and an accurac"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2303.01812","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-03-03T09:38:53Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"83005c86c12e299465f41bf7cff751d6f7092a4a8086c373d1b3f0d7b38b7616","abstract_canon_sha256":"3a36ce9b2334a04d37901f46925f322a2e730be7b140694f1686525c55d920d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:49.500628Z","signature_b64":"k29uWXPw5AekABsPJ44P+Hn/lcWxvxtBr4b2cAWtyaYgHaMY0c5vUGLjPbYo6kSujZ835SCIslC0gmHie4CLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58dc01d5221107ed14418f842911c7e704b2448cdb10d7a7ab8e4cbf2304fb4b","last_reissued_at":"2026-07-05T05:47:49.500198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:49.500198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heinrich Dinkel, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","submitted_at":"2023-03-03T09:38:53Z","abstract_excerpt":"Keyword spotting (KWS) is a core human-machine-interaction front-end task for most modern intelligent assistants. Recently, a unified (UniKW-AT) framework has been proposed that adds additional capabilities in the form of audio tagging (AT) to a KWS model. However, previous work did not consider the real-world deployment of a UniKW-AT model, where factors such as model size and inference speed are more important than performance alone. This work introduces three mobile-device deployable models named Unified Transformers (UiT). Our best model achieves an mAP of 34.09 on Audioset, and an accurac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01812","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.01812/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2303.01812","created_at":"2026-07-05T05:47:49.500258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.01812v1","created_at":"2026-07-05T05:47:49.500258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01812","created_at":"2026-07-05T05:47:49.500258+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDOADVJCCED6","created_at":"2026-07-05T05:47:49.500258+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDOADVJCCED62FCB","created_at":"2026-07-05T05:47:49.500258+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDOADVJC","created_at":"2026-07-05T05:47:49.500258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDOADVJCCED62FCBR6CCSEOH44","json":"https://pith.science/pith/LDOADVJCCED62FCBR6CCSEOH44.json","graph_json":"https://pith.science/api/pith-number/LDOADVJCCED62FCBR6CCSEOH44/graph.json","events_json":"https://pith.science/api/pith-number/LDOADVJCCED62FCBR6CCSEOH44/events.json","paper":"https://pith.science/paper/LDOADVJC"},"agent_actions":{"view_html":"https://pith.science/pith/LDOADVJCCED62FCBR6CCSEOH44","download_json":"https://pith.science/pith/LDOADVJCCED62FCBR6CCSEOH44.json","view_paper":"https://pith.science/paper/LDOADVJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.01812&json=true","fetch_graph":"https://pith.science/api/pith-number/LDOADVJCCED62FCBR6CCSEOH44/graph.json","fetch_events":"https://pith.science/api/pith-number/LDOADVJCCED62FCBR6CCSEOH44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDOADVJCCED62FCBR6CCSEOH44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDOADVJCCED62FCBR6CCSEOH44/action/storage_attestation","attest_author":"https://pith.science/pith/LDOADVJCCED62FCBR6CCSEOH44/action/author_attestation","sign_citation":"https://pith.science/pith/LDOADVJCCED62FCBR6CCSEOH44/action/citation_signature","submit_replication":"https://pith.science/pith/LDOADVJCCED62FCBR6CCSEOH44/action/replication_record"}},"created_at":"2026-07-05T05:47:49.500258+00:00","updated_at":"2026-07-05T05:47:49.500258+00:00"}