{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OWHV4ZD4YIGDYIKUD7BBQBXSNI","short_pith_number":"pith:OWHV4ZD4","schema_version":"1.0","canonical_sha256":"758f5e647cc20c3c21541fc21806f26a0849418e0759b48ec8a6a2a9357fb7e1","source":{"kind":"arxiv","id":"2505.13079","version":1},"attestation_state":"computed","paper":{"title":"Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Hisashi Kawai, Peng Shen, Xugang Lu, Yu Tsao","submitted_at":"2025-05-19T13:13:18Z","abstract_excerpt":"Transferring linguistic knowledge from a pretrained language model (PLM) to acoustic feature learning has proven effective in enhancing end-to-end automatic speech recognition (E2E-ASR). However, aligning representations between linguistic and acoustic modalities remains a challenge due to inherent modality gaps. Optimal transport (OT) has shown promise in mitigating these gaps by minimizing the Wasserstein distance (WD) between linguistic and acoustic feature distributions. However, previous OT-based methods overlook structural relationships, treating feature vectors as unordered sets. To add"},"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":"2505.13079","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-19T13:13:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b18a62d4ade86850b4214cd06de3e22ee1ae1f0f57b17a5477f4b12407440e66","abstract_canon_sha256":"5c6b25961d404de015ca3033773180db015d76c4c42e57b7a3d62073e09c6cef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:14.656360Z","signature_b64":"2RURN9guslvwz1Y36fZH1PT0Ty+e1XDpXWeC6UMXt1M3NJqwBL7/CzAdOosXUcGSJRityBLfxVLMRPRG41GwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"758f5e647cc20c3c21541fc21806f26a0849418e0759b48ec8a6a2a9357fb7e1","last_reissued_at":"2026-07-05T11:05:14.655901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:14.655901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Hisashi Kawai, Peng Shen, Xugang Lu, Yu Tsao","submitted_at":"2025-05-19T13:13:18Z","abstract_excerpt":"Transferring linguistic knowledge from a pretrained language model (PLM) to acoustic feature learning has proven effective in enhancing end-to-end automatic speech recognition (E2E-ASR). However, aligning representations between linguistic and acoustic modalities remains a challenge due to inherent modality gaps. Optimal transport (OT) has shown promise in mitigating these gaps by minimizing the Wasserstein distance (WD) between linguistic and acoustic feature distributions. However, previous OT-based methods overlook structural relationships, treating feature vectors as unordered sets. To add"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13079","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/2505.13079/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":"2505.13079","created_at":"2026-07-05T11:05:14.655957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13079v1","created_at":"2026-07-05T11:05:14.655957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13079","created_at":"2026-07-05T11:05:14.655957+00:00"},{"alias_kind":"pith_short_12","alias_value":"OWHV4ZD4YIGD","created_at":"2026-07-05T11:05:14.655957+00:00"},{"alias_kind":"pith_short_16","alias_value":"OWHV4ZD4YIGDYIKU","created_at":"2026-07-05T11:05:14.655957+00:00"},{"alias_kind":"pith_short_8","alias_value":"OWHV4ZD4","created_at":"2026-07-05T11:05:14.655957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13079","citing_title":"Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASR","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OWHV4ZD4YIGDYIKUD7BBQBXSNI","json":"https://pith.science/pith/OWHV4ZD4YIGDYIKUD7BBQBXSNI.json","graph_json":"https://pith.science/api/pith-number/OWHV4ZD4YIGDYIKUD7BBQBXSNI/graph.json","events_json":"https://pith.science/api/pith-number/OWHV4ZD4YIGDYIKUD7BBQBXSNI/events.json","paper":"https://pith.science/paper/OWHV4ZD4"},"agent_actions":{"view_html":"https://pith.science/pith/OWHV4ZD4YIGDYIKUD7BBQBXSNI","download_json":"https://pith.science/pith/OWHV4ZD4YIGDYIKUD7BBQBXSNI.json","view_paper":"https://pith.science/paper/OWHV4ZD4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13079&json=true","fetch_graph":"https://pith.science/api/pith-number/OWHV4ZD4YIGDYIKUD7BBQBXSNI/graph.json","fetch_events":"https://pith.science/api/pith-number/OWHV4ZD4YIGDYIKUD7BBQBXSNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OWHV4ZD4YIGDYIKUD7BBQBXSNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OWHV4ZD4YIGDYIKUD7BBQBXSNI/action/storage_attestation","attest_author":"https://pith.science/pith/OWHV4ZD4YIGDYIKUD7BBQBXSNI/action/author_attestation","sign_citation":"https://pith.science/pith/OWHV4ZD4YIGDYIKUD7BBQBXSNI/action/citation_signature","submit_replication":"https://pith.science/pith/OWHV4ZD4YIGDYIKUD7BBQBXSNI/action/replication_record"}},"created_at":"2026-07-05T11:05:14.655957+00:00","updated_at":"2026-07-05T11:05:14.655957+00:00"}