{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:O5VMLO2EYHFRT2IX7BLL4FCL5B","short_pith_number":"pith:O5VMLO2E","schema_version":"1.0","canonical_sha256":"776ac5bb44c1cb19e917f856be144be847505ef097b2391ea7e1b3a3589407da","source":{"kind":"arxiv","id":"1609.02082","version":1},"attestation_state":"computed","paper":{"title":"An improved uncertainty decoding scheme with weighted samples for DNN-HMM hybrid systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"cs.LG","authors_text":"Christian Huemmer, Ram\\'on Fern\\'andez Astudillo, Walter Kellermann","submitted_at":"2016-08-04T10:11:24Z","abstract_excerpt":"In this paper, we advance a recently-proposed uncertainty decoding scheme for DNN-HMM (deep neural network - hidden Markov model) hybrid systems. This numerical sampling concept averages DNN outputs produced by a finite set of feature samples (drawn from a probabilistic distortion model) to approximate the posterior likelihoods of the context-dependent HMM states. As main innovation, we propose a weighted DNN-output averaging based on a minimum classification error criterion and apply it to a probabilistic distortion model for spatial diffuseness features. The experimental evaluation is perfor"},"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":"1609.02082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-08-04T10:11:24Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"85132e6badbf0fa923af02354cb455ed80dee5f75718ce82ea87f94204655826","abstract_canon_sha256":"62c867604a91bb315a3f98f221c34338d61362259a4029ce692e2cf0c86c4353"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:05:09.201634Z","signature_b64":"wY7nY3A0nl936Zf8PhY2tTmz97LxCNNLNd8f0dnGXvrs+M8LVGDB3iFTdyWXL8kBSF9FXrneS2M0n6p/DNYcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"776ac5bb44c1cb19e917f856be144be847505ef097b2391ea7e1b3a3589407da","last_reissued_at":"2026-05-18T01:05:09.200897Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:05:09.200897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An improved uncertainty decoding scheme with weighted samples for DNN-HMM hybrid systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"cs.LG","authors_text":"Christian Huemmer, Ram\\'on Fern\\'andez Astudillo, Walter Kellermann","submitted_at":"2016-08-04T10:11:24Z","abstract_excerpt":"In this paper, we advance a recently-proposed uncertainty decoding scheme for DNN-HMM (deep neural network - hidden Markov model) hybrid systems. This numerical sampling concept averages DNN outputs produced by a finite set of feature samples (drawn from a probabilistic distortion model) to approximate the posterior likelihoods of the context-dependent HMM states. As main innovation, we propose a weighted DNN-output averaging based on a minimum classification error criterion and apply it to a probabilistic distortion model for spatial diffuseness features. The experimental evaluation is perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.02082","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":"1609.02082","created_at":"2026-05-18T01:05:09.201000+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.02082v1","created_at":"2026-05-18T01:05:09.201000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.02082","created_at":"2026-05-18T01:05:09.201000+00:00"},{"alias_kind":"pith_short_12","alias_value":"O5VMLO2EYHFR","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"O5VMLO2EYHFRT2IX","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"O5VMLO2E","created_at":"2026-05-18T12:30:36.002864+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/O5VMLO2EYHFRT2IX7BLL4FCL5B","json":"https://pith.science/pith/O5VMLO2EYHFRT2IX7BLL4FCL5B.json","graph_json":"https://pith.science/api/pith-number/O5VMLO2EYHFRT2IX7BLL4FCL5B/graph.json","events_json":"https://pith.science/api/pith-number/O5VMLO2EYHFRT2IX7BLL4FCL5B/events.json","paper":"https://pith.science/paper/O5VMLO2E"},"agent_actions":{"view_html":"https://pith.science/pith/O5VMLO2EYHFRT2IX7BLL4FCL5B","download_json":"https://pith.science/pith/O5VMLO2EYHFRT2IX7BLL4FCL5B.json","view_paper":"https://pith.science/paper/O5VMLO2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.02082&json=true","fetch_graph":"https://pith.science/api/pith-number/O5VMLO2EYHFRT2IX7BLL4FCL5B/graph.json","fetch_events":"https://pith.science/api/pith-number/O5VMLO2EYHFRT2IX7BLL4FCL5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O5VMLO2EYHFRT2IX7BLL4FCL5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O5VMLO2EYHFRT2IX7BLL4FCL5B/action/storage_attestation","attest_author":"https://pith.science/pith/O5VMLO2EYHFRT2IX7BLL4FCL5B/action/author_attestation","sign_citation":"https://pith.science/pith/O5VMLO2EYHFRT2IX7BLL4FCL5B/action/citation_signature","submit_replication":"https://pith.science/pith/O5VMLO2EYHFRT2IX7BLL4FCL5B/action/replication_record"}},"created_at":"2026-05-18T01:05:09.201000+00:00","updated_at":"2026-05-18T01:05:09.201000+00:00"}