{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7HY4DTTVJ2PWWY7Y6NBONPWQS2","short_pith_number":"pith:7HY4DTTV","schema_version":"1.0","canonical_sha256":"f9f1c1ce754e9f6b63f8f342e6bed096a0eebec8aff4e156d0fda529b1ea794a","source":{"kind":"arxiv","id":"2603.25041","version":2},"attestation_state":"computed","paper":{"title":"AdaLTM: Adaptive Layer-wise Task Vector Merging for Categorical Speech Emotion Recognition with ASR Knowledge Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chia-Yu Lee, Chi-Chun Lee, Huang-Cheng Chou, Shrikanth Narayanan, Tzu-Quan Lin, Ya-Tse Wu, Yuanchao Li","submitted_at":"2026-03-26T05:22:43Z","abstract_excerpt":"Integrating Automatic Speech Recognition (ASR) into Speech Emotion Recognition (SER) enhances modeling by providing linguistic context. However, conventional feature fusion faces performance bottlenecks, and multi-task learning often suffers from optimization conflicts. While task vectors and model merging have addressed such conflicts in NLP and CV, their potential in speech tasks remains largely unexplored. In this work, we propose an Adaptive Layer-wise Task Vector Merging (AdaLTM) framework based on WavLM-Large. Instead of joint optimization, we extract task vectors from in-domain ASR and "},"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":"2603.25041","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-03-26T05:22:43Z","cross_cats_sorted":[],"title_canon_sha256":"855eea31f04a6076ae1cbe59b79460681cf54d7665e128d3f28ab14a9ebb09ee","abstract_canon_sha256":"a5bef5434f03c9d30e2437a3e86c652713adae873884d1efe2a3aec5fc79bde4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:12:48.626741Z","signature_b64":"asd10zM0iVPevxoGfOxQltYhdhLWWOK8CXkpMH4WjK86MO66ub37riDzvEYPUIsjzRz/igA3qgUxkon6WQ+FAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9f1c1ce754e9f6b63f8f342e6bed096a0eebec8aff4e156d0fda529b1ea794a","last_reissued_at":"2026-06-23T02:12:48.626229Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:12:48.626229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaLTM: Adaptive Layer-wise Task Vector Merging for Categorical Speech Emotion Recognition with ASR Knowledge Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chia-Yu Lee, Chi-Chun Lee, Huang-Cheng Chou, Shrikanth Narayanan, Tzu-Quan Lin, Ya-Tse Wu, Yuanchao Li","submitted_at":"2026-03-26T05:22:43Z","abstract_excerpt":"Integrating Automatic Speech Recognition (ASR) into Speech Emotion Recognition (SER) enhances modeling by providing linguistic context. However, conventional feature fusion faces performance bottlenecks, and multi-task learning often suffers from optimization conflicts. While task vectors and model merging have addressed such conflicts in NLP and CV, their potential in speech tasks remains largely unexplored. In this work, we propose an Adaptive Layer-wise Task Vector Merging (AdaLTM) framework based on WavLM-Large. Instead of joint optimization, we extract task vectors from in-domain ASR and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.25041","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/2603.25041/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":"2603.25041","created_at":"2026-06-23T02:12:48.626287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.25041v2","created_at":"2026-06-23T02:12:48.626287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.25041","created_at":"2026-06-23T02:12:48.626287+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HY4DTTVJ2PW","created_at":"2026-06-23T02:12:48.626287+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HY4DTTVJ2PWWY7Y","created_at":"2026-06-23T02:12:48.626287+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HY4DTTV","created_at":"2026-06-23T02:12:48.626287+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/7HY4DTTVJ2PWWY7Y6NBONPWQS2","json":"https://pith.science/pith/7HY4DTTVJ2PWWY7Y6NBONPWQS2.json","graph_json":"https://pith.science/api/pith-number/7HY4DTTVJ2PWWY7Y6NBONPWQS2/graph.json","events_json":"https://pith.science/api/pith-number/7HY4DTTVJ2PWWY7Y6NBONPWQS2/events.json","paper":"https://pith.science/paper/7HY4DTTV"},"agent_actions":{"view_html":"https://pith.science/pith/7HY4DTTVJ2PWWY7Y6NBONPWQS2","download_json":"https://pith.science/pith/7HY4DTTVJ2PWWY7Y6NBONPWQS2.json","view_paper":"https://pith.science/paper/7HY4DTTV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.25041&json=true","fetch_graph":"https://pith.science/api/pith-number/7HY4DTTVJ2PWWY7Y6NBONPWQS2/graph.json","fetch_events":"https://pith.science/api/pith-number/7HY4DTTVJ2PWWY7Y6NBONPWQS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HY4DTTVJ2PWWY7Y6NBONPWQS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HY4DTTVJ2PWWY7Y6NBONPWQS2/action/storage_attestation","attest_author":"https://pith.science/pith/7HY4DTTVJ2PWWY7Y6NBONPWQS2/action/author_attestation","sign_citation":"https://pith.science/pith/7HY4DTTVJ2PWWY7Y6NBONPWQS2/action/citation_signature","submit_replication":"https://pith.science/pith/7HY4DTTVJ2PWWY7Y6NBONPWQS2/action/replication_record"}},"created_at":"2026-06-23T02:12:48.626287+00:00","updated_at":"2026-06-23T02:12:48.626287+00:00"}