{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:64JS5Y4Q3FLG2DA5GWEZSGGQMZ","short_pith_number":"pith:64JS5Y4Q","schema_version":"1.0","canonical_sha256":"f7132ee390d9566d0c1d35899918d0666155afe8872ae89d451c64be0341da8d","source":{"kind":"arxiv","id":"1610.03256","version":1},"attestation_state":"computed","paper":{"title":"GMM-Free Flat Start Sequence-Discriminative DNN Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"G\\'abor Gosztolya, L\\'aszl\\'o T\\'oth, Tam\\'as Gr\\'osz","submitted_at":"2016-10-11T09:52:57Z","abstract_excerpt":"Recently, attempts have been made to remove Gaussian mixture models (GMM) from the training process of deep neural network-based hidden Markov models (HMM/DNN). For the GMM-free training of a HMM/DNN hybrid we have to solve two problems, namely the initial alignment of the frame-level state labels and the creation of context-dependent states. Although flat-start training via iteratively realigning and retraining the DNN using a frame-level error function is viable, it is quite cumbersome. Here, we propose to use a sequence-discriminative training criterion for flat start. While sequence-discri"},"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":"1610.03256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-11T09:52:57Z","cross_cats_sorted":[],"title_canon_sha256":"0add4a6699afd3ea9455c33b420b086e50932b5023cb6c27920ff616dd446461","abstract_canon_sha256":"c10558051c6ad86814d4c6f4f11bfd10f39957d4e0d891d72c1461e2a15e09a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:02:12.083197Z","signature_b64":"1txfuKTMLqbnRsMC9zxGrOArDsXkR+PZOzqn/+AjuGVPNvQ7zDG4Lej9pzY6t3iPrrkfc73HIoEWCm0y06VxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7132ee390d9566d0c1d35899918d0666155afe8872ae89d451c64be0341da8d","last_reissued_at":"2026-05-18T01:02:12.082586Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:02:12.082586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GMM-Free Flat Start Sequence-Discriminative DNN Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"G\\'abor Gosztolya, L\\'aszl\\'o T\\'oth, Tam\\'as Gr\\'osz","submitted_at":"2016-10-11T09:52:57Z","abstract_excerpt":"Recently, attempts have been made to remove Gaussian mixture models (GMM) from the training process of deep neural network-based hidden Markov models (HMM/DNN). For the GMM-free training of a HMM/DNN hybrid we have to solve two problems, namely the initial alignment of the frame-level state labels and the creation of context-dependent states. Although flat-start training via iteratively realigning and retraining the DNN using a frame-level error function is viable, it is quite cumbersome. Here, we propose to use a sequence-discriminative training criterion for flat start. While sequence-discri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.03256","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":""},"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":"1610.03256","created_at":"2026-05-18T01:02:12.082695+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.03256v1","created_at":"2026-05-18T01:02:12.082695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.03256","created_at":"2026-05-18T01:02:12.082695+00:00"},{"alias_kind":"pith_short_12","alias_value":"64JS5Y4Q3FLG","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_16","alias_value":"64JS5Y4Q3FLG2DA5","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_8","alias_value":"64JS5Y4Q","created_at":"2026-05-18T12:30:01.593930+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/64JS5Y4Q3FLG2DA5GWEZSGGQMZ","json":"https://pith.science/pith/64JS5Y4Q3FLG2DA5GWEZSGGQMZ.json","graph_json":"https://pith.science/api/pith-number/64JS5Y4Q3FLG2DA5GWEZSGGQMZ/graph.json","events_json":"https://pith.science/api/pith-number/64JS5Y4Q3FLG2DA5GWEZSGGQMZ/events.json","paper":"https://pith.science/paper/64JS5Y4Q"},"agent_actions":{"view_html":"https://pith.science/pith/64JS5Y4Q3FLG2DA5GWEZSGGQMZ","download_json":"https://pith.science/pith/64JS5Y4Q3FLG2DA5GWEZSGGQMZ.json","view_paper":"https://pith.science/paper/64JS5Y4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.03256&json=true","fetch_graph":"https://pith.science/api/pith-number/64JS5Y4Q3FLG2DA5GWEZSGGQMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/64JS5Y4Q3FLG2DA5GWEZSGGQMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/64JS5Y4Q3FLG2DA5GWEZSGGQMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/64JS5Y4Q3FLG2DA5GWEZSGGQMZ/action/storage_attestation","attest_author":"https://pith.science/pith/64JS5Y4Q3FLG2DA5GWEZSGGQMZ/action/author_attestation","sign_citation":"https://pith.science/pith/64JS5Y4Q3FLG2DA5GWEZSGGQMZ/action/citation_signature","submit_replication":"https://pith.science/pith/64JS5Y4Q3FLG2DA5GWEZSGGQMZ/action/replication_record"}},"created_at":"2026-05-18T01:02:12.082695+00:00","updated_at":"2026-05-18T01:02:12.082695+00:00"}