{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WF4QS5ILVL7ZC65WDVPMDNTSCW","short_pith_number":"pith:WF4QS5IL","schema_version":"1.0","canonical_sha256":"b17909750baaff917bb61d5ec1b6721587a64c5312fbb6a0315a3ff1df43d331","source":{"kind":"arxiv","id":"2506.01496","version":2},"attestation_state":"computed","paper":{"title":"Continual Speech Learning with Fused Speech Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Gholamreza Haffari, Guilin Qi, Guitao Wang, Hao Yang, Jinming Zhao, Tongtong Wu","submitted_at":"2025-06-02T09:59:35Z","abstract_excerpt":"Rapid growth in speech data demands adaptive models, as traditional static methods fail to keep pace with dynamic and diverse speech information. We introduce continuous speech learning, a new set-up targeting at bridging the adaptation gap in current speech models. We use the encoder-decoder Whisper model to standardize speech tasks into a generative format. We integrate a learnable gated-fusion layer on the top of the encoder to dynamically select task-specific features for downstream tasks. Our approach improves accuracy significantly over traditional methods in six speech processing tasks,"},"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":"2506.01496","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T09:59:35Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"22da98cc170df0400a4f61627a6af233c1e1b339f09880d48050f72e1179578f","abstract_canon_sha256":"2fb9a817850d160e44f545693b9c1298f0ac1602e284d98aebc5bd00afa01563"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:01.425705Z","signature_b64":"kepbgH1LK2ZSv0gMjmfbhdJlGovEl/ES9l/XZE42hC8GVZz0X+bv4ZMEiJ5Lh83fto+Z36lz/BggWfus/Hc1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b17909750baaff917bb61d5ec1b6721587a64c5312fbb6a0315a3ff1df43d331","last_reissued_at":"2026-07-05T11:15:01.425184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:01.425184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Speech Learning with Fused Speech Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Gholamreza Haffari, Guilin Qi, Guitao Wang, Hao Yang, Jinming Zhao, Tongtong Wu","submitted_at":"2025-06-02T09:59:35Z","abstract_excerpt":"Rapid growth in speech data demands adaptive models, as traditional static methods fail to keep pace with dynamic and diverse speech information. We introduce continuous speech learning, a new set-up targeting at bridging the adaptation gap in current speech models. We use the encoder-decoder Whisper model to standardize speech tasks into a generative format. We integrate a learnable gated-fusion layer on the top of the encoder to dynamically select task-specific features for downstream tasks. Our approach improves accuracy significantly over traditional methods in six speech processing tasks,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01496","kind":"arxiv","version":2},"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/2506.01496/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":"2506.01496","created_at":"2026-07-05T11:15:01.425248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01496v2","created_at":"2026-07-05T11:15:01.425248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01496","created_at":"2026-07-05T11:15:01.425248+00:00"},{"alias_kind":"pith_short_12","alias_value":"WF4QS5ILVL7Z","created_at":"2026-07-05T11:15:01.425248+00:00"},{"alias_kind":"pith_short_16","alias_value":"WF4QS5ILVL7ZC65W","created_at":"2026-07-05T11:15:01.425248+00:00"},{"alias_kind":"pith_short_8","alias_value":"WF4QS5IL","created_at":"2026-07-05T11:15:01.425248+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01496","citing_title":"Continual Speech Learning with Fused Speech Features","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WF4QS5ILVL7ZC65WDVPMDNTSCW","json":"https://pith.science/pith/WF4QS5ILVL7ZC65WDVPMDNTSCW.json","graph_json":"https://pith.science/api/pith-number/WF4QS5ILVL7ZC65WDVPMDNTSCW/graph.json","events_json":"https://pith.science/api/pith-number/WF4QS5ILVL7ZC65WDVPMDNTSCW/events.json","paper":"https://pith.science/paper/WF4QS5IL"},"agent_actions":{"view_html":"https://pith.science/pith/WF4QS5ILVL7ZC65WDVPMDNTSCW","download_json":"https://pith.science/pith/WF4QS5ILVL7ZC65WDVPMDNTSCW.json","view_paper":"https://pith.science/paper/WF4QS5IL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01496&json=true","fetch_graph":"https://pith.science/api/pith-number/WF4QS5ILVL7ZC65WDVPMDNTSCW/graph.json","fetch_events":"https://pith.science/api/pith-number/WF4QS5ILVL7ZC65WDVPMDNTSCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WF4QS5ILVL7ZC65WDVPMDNTSCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WF4QS5ILVL7ZC65WDVPMDNTSCW/action/storage_attestation","attest_author":"https://pith.science/pith/WF4QS5ILVL7ZC65WDVPMDNTSCW/action/author_attestation","sign_citation":"https://pith.science/pith/WF4QS5ILVL7ZC65WDVPMDNTSCW/action/citation_signature","submit_replication":"https://pith.science/pith/WF4QS5ILVL7ZC65WDVPMDNTSCW/action/replication_record"}},"created_at":"2026-07-05T11:15:01.425248+00:00","updated_at":"2026-07-05T11:15:01.425248+00:00"}