{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SNGFX6OT2CC3YVZS3SZ4VIHPH2","short_pith_number":"pith:SNGFX6OT","schema_version":"1.0","canonical_sha256":"934c5bf9d3d085bc5732dcb3caa0ef3eb524bd05b18b7e96ef89f27406c6375f","source":{"kind":"arxiv","id":"1809.07832","version":2},"attestation_state":"computed","paper":{"title":"LSTM-based Whisper Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ariya Rastrow, Bj\\\"orn Hoffmeister, Chengyuan Ma, Jiacheng Gu, Kellen Gillespie, Roland Maas, Thomas Drugman, Zeynab Raeesy, Zhenpei Yang","submitted_at":"2018-09-20T20:04:07Z","abstract_excerpt":"This article presents a whisper speech detector in the far-field domain. The proposed system consists of a long-short term memory (LSTM) neural network trained on log-filterbank energy (LFBE) acoustic features. This model is trained and evaluated on recordings of human interactions with voice-controlled, far-field devices in whisper and normal phonation modes. We compare multiple inference approaches for utterance-level classification by examining trajectories of the LSTM posteriors. In addition, we engineer a set of features based on the signal characteristics inherent to whisper speech, and "},"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":"1809.07832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-20T20:04:07Z","cross_cats_sorted":[],"title_canon_sha256":"74f5ce81357c54a696ffd2f6e50e665720551833267acb5f07abecedfa2a288f","abstract_canon_sha256":"6b017d743dd6e50b5681eff3ae5fb5b53ffa6925f794f942a87a937e1df5e058"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:44.774099Z","signature_b64":"3N2bISc8n0gmW4q4NHOzCtK7GaUuF8rNoQHz+XOJ0zV6fXPTusKZIDvdjZ696PwAVW3odv5Vk1I7ksi2z4vEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"934c5bf9d3d085bc5732dcb3caa0ef3eb524bd05b18b7e96ef89f27406c6375f","last_reissued_at":"2026-07-05T00:52:44.773624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:44.773624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LSTM-based Whisper Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ariya Rastrow, Bj\\\"orn Hoffmeister, Chengyuan Ma, Jiacheng Gu, Kellen Gillespie, Roland Maas, Thomas Drugman, Zeynab Raeesy, Zhenpei Yang","submitted_at":"2018-09-20T20:04:07Z","abstract_excerpt":"This article presents a whisper speech detector in the far-field domain. The proposed system consists of a long-short term memory (LSTM) neural network trained on log-filterbank energy (LFBE) acoustic features. This model is trained and evaluated on recordings of human interactions with voice-controlled, far-field devices in whisper and normal phonation modes. We compare multiple inference approaches for utterance-level classification by examining trajectories of the LSTM posteriors. In addition, we engineer a set of features based on the signal characteristics inherent to whisper speech, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.07832","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1809.07832/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":"1809.07832","created_at":"2026-07-05T00:52:44.773680+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.07832v2","created_at":"2026-07-05T00:52:44.773680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.07832","created_at":"2026-07-05T00:52:44.773680+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNGFX6OT2CC3","created_at":"2026-07-05T00:52:44.773680+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNGFX6OT2CC3YVZS","created_at":"2026-07-05T00:52:44.773680+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNGFX6OT","created_at":"2026-07-05T00:52:44.773680+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/SNGFX6OT2CC3YVZS3SZ4VIHPH2","json":"https://pith.science/pith/SNGFX6OT2CC3YVZS3SZ4VIHPH2.json","graph_json":"https://pith.science/api/pith-number/SNGFX6OT2CC3YVZS3SZ4VIHPH2/graph.json","events_json":"https://pith.science/api/pith-number/SNGFX6OT2CC3YVZS3SZ4VIHPH2/events.json","paper":"https://pith.science/paper/SNGFX6OT"},"agent_actions":{"view_html":"https://pith.science/pith/SNGFX6OT2CC3YVZS3SZ4VIHPH2","download_json":"https://pith.science/pith/SNGFX6OT2CC3YVZS3SZ4VIHPH2.json","view_paper":"https://pith.science/paper/SNGFX6OT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.07832&json=true","fetch_graph":"https://pith.science/api/pith-number/SNGFX6OT2CC3YVZS3SZ4VIHPH2/graph.json","fetch_events":"https://pith.science/api/pith-number/SNGFX6OT2CC3YVZS3SZ4VIHPH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNGFX6OT2CC3YVZS3SZ4VIHPH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNGFX6OT2CC3YVZS3SZ4VIHPH2/action/storage_attestation","attest_author":"https://pith.science/pith/SNGFX6OT2CC3YVZS3SZ4VIHPH2/action/author_attestation","sign_citation":"https://pith.science/pith/SNGFX6OT2CC3YVZS3SZ4VIHPH2/action/citation_signature","submit_replication":"https://pith.science/pith/SNGFX6OT2CC3YVZS3SZ4VIHPH2/action/replication_record"}},"created_at":"2026-07-05T00:52:44.773680+00:00","updated_at":"2026-07-05T00:52:44.773680+00:00"}