{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YJHRT6HXG3KEFFTE4NTUN4T7PD","short_pith_number":"pith:YJHRT6HX","schema_version":"1.0","canonical_sha256":"c24f19f8f736d4429664e36746f27f78f789e66a30ad9d9fe85a1826e925a590","source":{"kind":"arxiv","id":"2303.03600","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Knowledge Distillation between Text and Speech Pre-trained Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bin Ma, Chong Zhang, Dianwen Ng, Erik Cambria, Han Lei, Jinjie Ni, Qian Chen, Trung Hieu Nguyen, Wen Wang, Yukun Ma","submitted_at":"2023-03-07T02:31:57Z","abstract_excerpt":"Learning on a massive amount of speech corpus leads to the recent success of many self-supervised speech models. With knowledge distillation, these models may also benefit from the knowledge encoded by language models that are pre-trained on rich sources of texts. The distillation process, however, is challenging due to the modal disparity between textual and speech embedding spaces. This paper studies metric-based distillation to align the embedding space of text and speech with only a small amount of data without modifying the model structure. Since the semantic and granularity gap between t"},"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":"2303.03600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-07T02:31:57Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"5b229f4e150f704013fd1b0b8f2c36b7cd167c7861c0b00d3c183ea18afe6100","abstract_canon_sha256":"20e2a1af01d9e7f97367f64c7bbf1989d2f81409f20e865f3a57a584a8870756"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:56.579062Z","signature_b64":"UYhAXwIspE8u5IE6kVHHysnhir1noaZXu3BODeje3qZC43CDx/4WakMbRBazX00zkv7qLLDUX4Q1HRl3Xb8gBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c24f19f8f736d4429664e36746f27f78f789e66a30ad9d9fe85a1826e925a590","last_reissued_at":"2026-07-05T05:48:56.578570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:56.578570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Knowledge Distillation between Text and Speech Pre-trained Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bin Ma, Chong Zhang, Dianwen Ng, Erik Cambria, Han Lei, Jinjie Ni, Qian Chen, Trung Hieu Nguyen, Wen Wang, Yukun Ma","submitted_at":"2023-03-07T02:31:57Z","abstract_excerpt":"Learning on a massive amount of speech corpus leads to the recent success of many self-supervised speech models. With knowledge distillation, these models may also benefit from the knowledge encoded by language models that are pre-trained on rich sources of texts. The distillation process, however, is challenging due to the modal disparity between textual and speech embedding spaces. This paper studies metric-based distillation to align the embedding space of text and speech with only a small amount of data without modifying the model structure. Since the semantic and granularity gap between t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03600","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/2303.03600/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":"2303.03600","created_at":"2026-07-05T05:48:56.578633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03600v1","created_at":"2026-07-05T05:48:56.578633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03600","created_at":"2026-07-05T05:48:56.578633+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJHRT6HXG3KE","created_at":"2026-07-05T05:48:56.578633+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJHRT6HXG3KEFFTE","created_at":"2026-07-05T05:48:56.578633+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJHRT6HX","created_at":"2026-07-05T05:48:56.578633+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/YJHRT6HXG3KEFFTE4NTUN4T7PD","json":"https://pith.science/pith/YJHRT6HXG3KEFFTE4NTUN4T7PD.json","graph_json":"https://pith.science/api/pith-number/YJHRT6HXG3KEFFTE4NTUN4T7PD/graph.json","events_json":"https://pith.science/api/pith-number/YJHRT6HXG3KEFFTE4NTUN4T7PD/events.json","paper":"https://pith.science/paper/YJHRT6HX"},"agent_actions":{"view_html":"https://pith.science/pith/YJHRT6HXG3KEFFTE4NTUN4T7PD","download_json":"https://pith.science/pith/YJHRT6HXG3KEFFTE4NTUN4T7PD.json","view_paper":"https://pith.science/paper/YJHRT6HX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03600&json=true","fetch_graph":"https://pith.science/api/pith-number/YJHRT6HXG3KEFFTE4NTUN4T7PD/graph.json","fetch_events":"https://pith.science/api/pith-number/YJHRT6HXG3KEFFTE4NTUN4T7PD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJHRT6HXG3KEFFTE4NTUN4T7PD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJHRT6HXG3KEFFTE4NTUN4T7PD/action/storage_attestation","attest_author":"https://pith.science/pith/YJHRT6HXG3KEFFTE4NTUN4T7PD/action/author_attestation","sign_citation":"https://pith.science/pith/YJHRT6HXG3KEFFTE4NTUN4T7PD/action/citation_signature","submit_replication":"https://pith.science/pith/YJHRT6HXG3KEFFTE4NTUN4T7PD/action/replication_record"}},"created_at":"2026-07-05T05:48:56.578633+00:00","updated_at":"2026-07-05T05:48:56.578633+00:00"}