{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BGKCBVBDARV7JSTU66MUXRMIC4","short_pith_number":"pith:BGKCBVBD","schema_version":"1.0","canonical_sha256":"099420d423046bf4ca74f7994bc588173d6683b0e9595de920b8ce313e50da4d","source":{"kind":"arxiv","id":"2407.10603","version":1},"attestation_state":"computed","paper":{"title":"Leave No Knowledge Behind During Knowledge Distillation: Towards Practical and Effective Knowledge Distillation for Code-Switching ASR Using Realistic Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Cheng-Kuang Lee, Hung-yi Lee, Liang-Hsuan Tseng, Tsung-Ren Huang, Wei-Shun Chang, Zih-Ching Chen","submitted_at":"2024-07-15T10:25:14Z","abstract_excerpt":"Recent advances in automatic speech recognition (ASR) often rely on large speech foundation models for generating high-quality transcriptions. However, these models can be impractical due to limited computing resources. The situation is even more severe in terms of more realistic or difficult scenarios, such as code-switching ASR (CS-ASR). To address this, we present a framework for developing more efficient models for CS-ASR through knowledge distillation using realistic speech-only data. Our proposed method, Leave No Knowledge Behind During Knowledge Distillation (K$^2$D), leverages both the"},"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":"2407.10603","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-15T10:25:14Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"74a2c7fa8ad5573b948ec21d3a492de30f14e10af1d59e54722cfccbf72d946e","abstract_canon_sha256":"d7c4618a7ef0422c749ab611f2bed9633a53e14f58abbf0cdbc8e424b3739198"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:01.774551Z","signature_b64":"onndPM/tN4fOZ5IV/p0uZsd4+2EduS/zRSYWXGVloGA5TA1wK+BR3GAQMHtuUIYV7flraDq2n5LZKSXPoMW7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"099420d423046bf4ca74f7994bc588173d6683b0e9595de920b8ce313e50da4d","last_reissued_at":"2026-07-05T08:44:01.774095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:01.774095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leave No Knowledge Behind During Knowledge Distillation: Towards Practical and Effective Knowledge Distillation for Code-Switching ASR Using Realistic Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Cheng-Kuang Lee, Hung-yi Lee, Liang-Hsuan Tseng, Tsung-Ren Huang, Wei-Shun Chang, Zih-Ching Chen","submitted_at":"2024-07-15T10:25:14Z","abstract_excerpt":"Recent advances in automatic speech recognition (ASR) often rely on large speech foundation models for generating high-quality transcriptions. However, these models can be impractical due to limited computing resources. The situation is even more severe in terms of more realistic or difficult scenarios, such as code-switching ASR (CS-ASR). To address this, we present a framework for developing more efficient models for CS-ASR through knowledge distillation using realistic speech-only data. Our proposed method, Leave No Knowledge Behind During Knowledge Distillation (K$^2$D), leverages both the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10603","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/2407.10603/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":"2407.10603","created_at":"2026-07-05T08:44:01.774153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10603v1","created_at":"2026-07-05T08:44:01.774153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10603","created_at":"2026-07-05T08:44:01.774153+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGKCBVBDARV7","created_at":"2026-07-05T08:44:01.774153+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGKCBVBDARV7JSTU","created_at":"2026-07-05T08:44:01.774153+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGKCBVBD","created_at":"2026-07-05T08:44:01.774153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14190","citing_title":"AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGKCBVBDARV7JSTU66MUXRMIC4","json":"https://pith.science/pith/BGKCBVBDARV7JSTU66MUXRMIC4.json","graph_json":"https://pith.science/api/pith-number/BGKCBVBDARV7JSTU66MUXRMIC4/graph.json","events_json":"https://pith.science/api/pith-number/BGKCBVBDARV7JSTU66MUXRMIC4/events.json","paper":"https://pith.science/paper/BGKCBVBD"},"agent_actions":{"view_html":"https://pith.science/pith/BGKCBVBDARV7JSTU66MUXRMIC4","download_json":"https://pith.science/pith/BGKCBVBDARV7JSTU66MUXRMIC4.json","view_paper":"https://pith.science/paper/BGKCBVBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10603&json=true","fetch_graph":"https://pith.science/api/pith-number/BGKCBVBDARV7JSTU66MUXRMIC4/graph.json","fetch_events":"https://pith.science/api/pith-number/BGKCBVBDARV7JSTU66MUXRMIC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGKCBVBDARV7JSTU66MUXRMIC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGKCBVBDARV7JSTU66MUXRMIC4/action/storage_attestation","attest_author":"https://pith.science/pith/BGKCBVBDARV7JSTU66MUXRMIC4/action/author_attestation","sign_citation":"https://pith.science/pith/BGKCBVBDARV7JSTU66MUXRMIC4/action/citation_signature","submit_replication":"https://pith.science/pith/BGKCBVBDARV7JSTU66MUXRMIC4/action/replication_record"}},"created_at":"2026-07-05T08:44:01.774153+00:00","updated_at":"2026-07-05T08:44:01.774153+00:00"}