{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5YJZ36FZ62MXDMO4WHFYPTCVXN","short_pith_number":"pith:5YJZ36FZ","schema_version":"1.0","canonical_sha256":"ee139df8b9f69971b1dcb1cb87cc55bb60f037cf008ed78d483352b6b94965df","source":{"kind":"arxiv","id":"1904.08311","version":2},"attestation_state":"computed","paper":{"title":"Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gakuto Kurata, Kartik Audhkhasi","submitted_at":"2019-04-17T15:18:23Z","abstract_excerpt":"Conventional automatic speech recognition (ASR) systems trained from frame-level alignments can easily leverage posterior fusion to improve ASR accuracy and build a better single model with knowledge distillation. End-to-end ASR systems trained using the Connectionist Temporal Classification (CTC) loss do not require frame-level alignment and hence simplify model training. However, sparse and arbitrary posterior spike timings from CTC models pose a new set of challenges in posterior fusion from multiple models and knowledge distillation between CTC models. We propose a method to train a CTC mo"},"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":"1904.08311","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-17T15:18:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9388470b25e77ff62f4f9758e8bc4dd2aa23a9f2183fab622d645719fca21444","abstract_canon_sha256":"a035b4190618008b97e738c76aa413cc8e7cf0dac198ac06c13cbf7669be87f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:42.346824Z","signature_b64":"JvPqmSiQ0WFDpWDkbO4wpq3GC14GkDQizYJY3xL7nu6rnfHo9stmax6UCYeAZ0557FZeDXIgOg4HXx/zGR2hCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee139df8b9f69971b1dcb1cb87cc55bb60f037cf008ed78d483352b6b94965df","last_reissued_at":"2026-05-17T23:41:42.346260Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:42.346260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gakuto Kurata, Kartik Audhkhasi","submitted_at":"2019-04-17T15:18:23Z","abstract_excerpt":"Conventional automatic speech recognition (ASR) systems trained from frame-level alignments can easily leverage posterior fusion to improve ASR accuracy and build a better single model with knowledge distillation. End-to-end ASR systems trained using the Connectionist Temporal Classification (CTC) loss do not require frame-level alignment and hence simplify model training. However, sparse and arbitrary posterior spike timings from CTC models pose a new set of challenges in posterior fusion from multiple models and knowledge distillation between CTC models. We propose a method to train a CTC mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08311","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":""},"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":"1904.08311","created_at":"2026-05-17T23:41:42.346326+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.08311v2","created_at":"2026-05-17T23:41:42.346326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08311","created_at":"2026-05-17T23:41:42.346326+00:00"},{"alias_kind":"pith_short_12","alias_value":"5YJZ36FZ62MX","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5YJZ36FZ62MXDMO4","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5YJZ36FZ","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22069","citing_title":"Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASR","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5YJZ36FZ62MXDMO4WHFYPTCVXN","json":"https://pith.science/pith/5YJZ36FZ62MXDMO4WHFYPTCVXN.json","graph_json":"https://pith.science/api/pith-number/5YJZ36FZ62MXDMO4WHFYPTCVXN/graph.json","events_json":"https://pith.science/api/pith-number/5YJZ36FZ62MXDMO4WHFYPTCVXN/events.json","paper":"https://pith.science/paper/5YJZ36FZ"},"agent_actions":{"view_html":"https://pith.science/pith/5YJZ36FZ62MXDMO4WHFYPTCVXN","download_json":"https://pith.science/pith/5YJZ36FZ62MXDMO4WHFYPTCVXN.json","view_paper":"https://pith.science/paper/5YJZ36FZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.08311&json=true","fetch_graph":"https://pith.science/api/pith-number/5YJZ36FZ62MXDMO4WHFYPTCVXN/graph.json","fetch_events":"https://pith.science/api/pith-number/5YJZ36FZ62MXDMO4WHFYPTCVXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5YJZ36FZ62MXDMO4WHFYPTCVXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5YJZ36FZ62MXDMO4WHFYPTCVXN/action/storage_attestation","attest_author":"https://pith.science/pith/5YJZ36FZ62MXDMO4WHFYPTCVXN/action/author_attestation","sign_citation":"https://pith.science/pith/5YJZ36FZ62MXDMO4WHFYPTCVXN/action/citation_signature","submit_replication":"https://pith.science/pith/5YJZ36FZ62MXDMO4WHFYPTCVXN/action/replication_record"}},"created_at":"2026-05-17T23:41:42.346326+00:00","updated_at":"2026-05-17T23:41:42.346326+00:00"}