{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3YV5LM2ZGHKJTHHKU2PBVE5SED","short_pith_number":"pith:3YV5LM2Z","schema_version":"1.0","canonical_sha256":"de2bd5b35931d4999ceaa69e1a93b220f36beae76b11b242eb871b1e370ff586","source":{"kind":"arxiv","id":"1806.08404","version":2},"attestation_state":"computed","paper":{"title":"On the Relationship Between Short-Time Objective Intelligibility and Short-Time Spectral-Amplitude Mean-Square Error for Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jesper Jensen, Morten Kolb{\\ae}k, Zheng-Hua Tan","submitted_at":"2018-06-21T19:07:12Z","abstract_excerpt":"The majority of deep neural network (DNN) based speech enhancement algorithms rely on the mean-square error (MSE) criterion of short-time spectral amplitudes (STSA), which has no apparent link to human perception, e.g. speech intelligibility. Short-Time Objective Intelligibility (STOI), a popular state-of-the-art speech intelligibility estimator, on the other hand, relies on linear correlation of speech temporal envelopes. This raises the question if a DNN training criterion based on envelope linear correlation (ELC) can lead to improved speech intelligibility performance of DNN based speech e"},"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":"1806.08404","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-06-21T19:07:12Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"b61e601df42e073b46548563afca0bee5d4d400039a984616d38ff4ca4b3b3d5","abstract_canon_sha256":"0e5fecc82bcb7004e70675fed516ff562fe6cdab776d5263d319a4148c85e301"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:16.885861Z","signature_b64":"CWnEY2Tl7202+jApfyU6oSfikVAaKZKDGBFMqi4X0mILWpOqVqEIEPcmLzSS3gEJr3SRZEcGEJjGnhRwuwHXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de2bd5b35931d4999ceaa69e1a93b220f36beae76b11b242eb871b1e370ff586","last_reissued_at":"2026-05-17T23:59:16.885449Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:16.885449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Relationship Between Short-Time Objective Intelligibility and Short-Time Spectral-Amplitude Mean-Square Error for Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jesper Jensen, Morten Kolb{\\ae}k, Zheng-Hua Tan","submitted_at":"2018-06-21T19:07:12Z","abstract_excerpt":"The majority of deep neural network (DNN) based speech enhancement algorithms rely on the mean-square error (MSE) criterion of short-time spectral amplitudes (STSA), which has no apparent link to human perception, e.g. speech intelligibility. Short-Time Objective Intelligibility (STOI), a popular state-of-the-art speech intelligibility estimator, on the other hand, relies on linear correlation of speech temporal envelopes. This raises the question if a DNN training criterion based on envelope linear correlation (ELC) can lead to improved speech intelligibility performance of DNN based speech e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08404","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":"1806.08404","created_at":"2026-05-17T23:59:16.885500+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.08404v2","created_at":"2026-05-17T23:59:16.885500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08404","created_at":"2026-05-17T23:59:16.885500+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YV5LM2ZGHKJ","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YV5LM2ZGHKJTHHK","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YV5LM2Z","created_at":"2026-05-18T12:32:05.422762+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/3YV5LM2ZGHKJTHHKU2PBVE5SED","json":"https://pith.science/pith/3YV5LM2ZGHKJTHHKU2PBVE5SED.json","graph_json":"https://pith.science/api/pith-number/3YV5LM2ZGHKJTHHKU2PBVE5SED/graph.json","events_json":"https://pith.science/api/pith-number/3YV5LM2ZGHKJTHHKU2PBVE5SED/events.json","paper":"https://pith.science/paper/3YV5LM2Z"},"agent_actions":{"view_html":"https://pith.science/pith/3YV5LM2ZGHKJTHHKU2PBVE5SED","download_json":"https://pith.science/pith/3YV5LM2ZGHKJTHHKU2PBVE5SED.json","view_paper":"https://pith.science/paper/3YV5LM2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.08404&json=true","fetch_graph":"https://pith.science/api/pith-number/3YV5LM2ZGHKJTHHKU2PBVE5SED/graph.json","fetch_events":"https://pith.science/api/pith-number/3YV5LM2ZGHKJTHHKU2PBVE5SED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YV5LM2ZGHKJTHHKU2PBVE5SED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YV5LM2ZGHKJTHHKU2PBVE5SED/action/storage_attestation","attest_author":"https://pith.science/pith/3YV5LM2ZGHKJTHHKU2PBVE5SED/action/author_attestation","sign_citation":"https://pith.science/pith/3YV5LM2ZGHKJTHHKU2PBVE5SED/action/citation_signature","submit_replication":"https://pith.science/pith/3YV5LM2ZGHKJTHHKU2PBVE5SED/action/replication_record"}},"created_at":"2026-05-17T23:59:16.885500+00:00","updated_at":"2026-05-17T23:59:16.885500+00:00"}