{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PSOFMZP3TXZQM4AECCA23E6WSS","short_pith_number":"pith:PSOFMZP3","schema_version":"1.0","canonical_sha256":"7c9c5665fb9df30670041081ad93d694b0718cf929a56130f425ba534da1dee1","source":{"kind":"arxiv","id":"2412.00877","version":1},"attestation_state":"computed","paper":{"title":"Complexity boosted adaptive training for better low resource ASR performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Biao Li, Hongxuan Lu, Shenjian Wang","submitted_at":"2024-12-01T16:32:49Z","abstract_excerpt":"During the entire training process of the ASR model, the intensity of data augmentation and the approach of calculating training loss are applied in a regulated manner based on preset parameters. For example, SpecAugment employs a predefined strength of augmentation to mask parts of the time-frequency domain spectrum. Similarly, in CTC-based multi-layer models, the loss is generally determined based on the output of the encoder's final layer during the training process. However, ignoring dynamic characteristics may suboptimally train models. To address the issue, we present a two-stage trainin"},"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":"2412.00877","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-01T16:32:49Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"a0f7bd0f9e4828da54f5bfe195346a5e1b4cdea949dbfd07f553f2a6134745a0","abstract_canon_sha256":"5073fa330393e3dd015395e35b26641525a94079bf8a0841dfe56436fc82278d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:49.732919Z","signature_b64":"SXy6aAJ18ThjgE/2KgjSXfBefBbbsP2v3s34bd31GmUNP7vMuPDQnmadJv6AbSky8fGJ8OEf1HcBxcEXOazwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c9c5665fb9df30670041081ad93d694b0718cf929a56130f425ba534da1dee1","last_reissued_at":"2026-07-05T09:42:49.732400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:49.732400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complexity boosted adaptive training for better low resource ASR performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Biao Li, Hongxuan Lu, Shenjian Wang","submitted_at":"2024-12-01T16:32:49Z","abstract_excerpt":"During the entire training process of the ASR model, the intensity of data augmentation and the approach of calculating training loss are applied in a regulated manner based on preset parameters. For example, SpecAugment employs a predefined strength of augmentation to mask parts of the time-frequency domain spectrum. Similarly, in CTC-based multi-layer models, the loss is generally determined based on the output of the encoder's final layer during the training process. However, ignoring dynamic characteristics may suboptimally train models. To address the issue, we present a two-stage trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00877","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/2412.00877/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":"2412.00877","created_at":"2026-07-05T09:42:49.732471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00877v1","created_at":"2026-07-05T09:42:49.732471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00877","created_at":"2026-07-05T09:42:49.732471+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSOFMZP3TXZQ","created_at":"2026-07-05T09:42:49.732471+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSOFMZP3TXZQM4AE","created_at":"2026-07-05T09:42:49.732471+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSOFMZP3","created_at":"2026-07-05T09:42:49.732471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00877","citing_title":"Complexity boosted adaptive training for better low resource ASR performance","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PSOFMZP3TXZQM4AECCA23E6WSS","json":"https://pith.science/pith/PSOFMZP3TXZQM4AECCA23E6WSS.json","graph_json":"https://pith.science/api/pith-number/PSOFMZP3TXZQM4AECCA23E6WSS/graph.json","events_json":"https://pith.science/api/pith-number/PSOFMZP3TXZQM4AECCA23E6WSS/events.json","paper":"https://pith.science/paper/PSOFMZP3"},"agent_actions":{"view_html":"https://pith.science/pith/PSOFMZP3TXZQM4AECCA23E6WSS","download_json":"https://pith.science/pith/PSOFMZP3TXZQM4AECCA23E6WSS.json","view_paper":"https://pith.science/paper/PSOFMZP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00877&json=true","fetch_graph":"https://pith.science/api/pith-number/PSOFMZP3TXZQM4AECCA23E6WSS/graph.json","fetch_events":"https://pith.science/api/pith-number/PSOFMZP3TXZQM4AECCA23E6WSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSOFMZP3TXZQM4AECCA23E6WSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSOFMZP3TXZQM4AECCA23E6WSS/action/storage_attestation","attest_author":"https://pith.science/pith/PSOFMZP3TXZQM4AECCA23E6WSS/action/author_attestation","sign_citation":"https://pith.science/pith/PSOFMZP3TXZQM4AECCA23E6WSS/action/citation_signature","submit_replication":"https://pith.science/pith/PSOFMZP3TXZQM4AECCA23E6WSS/action/replication_record"}},"created_at":"2026-07-05T09:42:49.732471+00:00","updated_at":"2026-07-05T09:42:49.732471+00:00"}