{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BTDPUBZ6MM2ATGSDWNSG5Q2LUE","short_pith_number":"pith:BTDPUBZ6","schema_version":"1.0","canonical_sha256":"0cc6fa073e6334099a43b3646ec34ba111946ba9be6af017424fe4da492f7093","source":{"kind":"arxiv","id":"2607.02129","version":1},"attestation_state":"computed","paper":{"title":"Speaker head orientation estimation with a single microphone array using phase spectrogram features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Archontis Politis, Balint Turi, Parthasaarathy Sudarsanam, Tuomas Virtanen","submitted_at":"2026-07-02T13:05:36Z","abstract_excerpt":"Estimating a speaker's head orientation from audio can provide valuable information in smart environments, meetings, and driver monitoring. We propose a novel approach that leverages the phase component of the short-time Fourier transform from a single microphone array as input to a deep neural network combining convolutional, recurrent, and self-attention layers. Unlike prior methods that use physics-informed handcrafted features or raw waveform inputs, our approach enables robust learning from simulated and real data. Trained on a large-scale dataset generated with voice directivity patterns"},"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":"2607.02129","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-02T13:05:36Z","cross_cats_sorted":[],"title_canon_sha256":"d099f24ec8dc41cd9eb176fa56e70402f448b1433dfa53b9ba85a69fd92b05e0","abstract_canon_sha256":"de8c4ccf4537d6f023ae86722c1a708392aaff4c0d2ee4b6aafab1ad0ca3dd9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:43.000820Z","signature_b64":"1whNWlXzoHsclebUX7CRNn1u+gpCuhWybEAmg2Fu5iqZcw5yal2TJ6WdnvOHDglV3YMJW0ZIC09mj8l3w4IADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cc6fa073e6334099a43b3646ec34ba111946ba9be6af017424fe4da492f7093","last_reissued_at":"2026-07-03T01:17:43.000414Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:43.000414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaker head orientation estimation with a single microphone array using phase spectrogram features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Archontis Politis, Balint Turi, Parthasaarathy Sudarsanam, Tuomas Virtanen","submitted_at":"2026-07-02T13:05:36Z","abstract_excerpt":"Estimating a speaker's head orientation from audio can provide valuable information in smart environments, meetings, and driver monitoring. We propose a novel approach that leverages the phase component of the short-time Fourier transform from a single microphone array as input to a deep neural network combining convolutional, recurrent, and self-attention layers. Unlike prior methods that use physics-informed handcrafted features or raw waveform inputs, our approach enables robust learning from simulated and real data. Trained on a large-scale dataset generated with voice directivity patterns"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02129","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.02129/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":"2607.02129","created_at":"2026-07-03T01:17:43.000474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02129v1","created_at":"2026-07-03T01:17:43.000474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02129","created_at":"2026-07-03T01:17:43.000474+00:00"},{"alias_kind":"pith_short_12","alias_value":"BTDPUBZ6MM2A","created_at":"2026-07-03T01:17:43.000474+00:00"},{"alias_kind":"pith_short_16","alias_value":"BTDPUBZ6MM2ATGSD","created_at":"2026-07-03T01:17:43.000474+00:00"},{"alias_kind":"pith_short_8","alias_value":"BTDPUBZ6","created_at":"2026-07-03T01:17:43.000474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.02129","citing_title":"Speaker head orientation estimation with a single microphone array using phase spectrogram features","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BTDPUBZ6MM2ATGSDWNSG5Q2LUE","json":"https://pith.science/pith/BTDPUBZ6MM2ATGSDWNSG5Q2LUE.json","graph_json":"https://pith.science/api/pith-number/BTDPUBZ6MM2ATGSDWNSG5Q2LUE/graph.json","events_json":"https://pith.science/api/pith-number/BTDPUBZ6MM2ATGSDWNSG5Q2LUE/events.json","paper":"https://pith.science/paper/BTDPUBZ6"},"agent_actions":{"view_html":"https://pith.science/pith/BTDPUBZ6MM2ATGSDWNSG5Q2LUE","download_json":"https://pith.science/pith/BTDPUBZ6MM2ATGSDWNSG5Q2LUE.json","view_paper":"https://pith.science/paper/BTDPUBZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02129&json=true","fetch_graph":"https://pith.science/api/pith-number/BTDPUBZ6MM2ATGSDWNSG5Q2LUE/graph.json","fetch_events":"https://pith.science/api/pith-number/BTDPUBZ6MM2ATGSDWNSG5Q2LUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BTDPUBZ6MM2ATGSDWNSG5Q2LUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BTDPUBZ6MM2ATGSDWNSG5Q2LUE/action/storage_attestation","attest_author":"https://pith.science/pith/BTDPUBZ6MM2ATGSDWNSG5Q2LUE/action/author_attestation","sign_citation":"https://pith.science/pith/BTDPUBZ6MM2ATGSDWNSG5Q2LUE/action/citation_signature","submit_replication":"https://pith.science/pith/BTDPUBZ6MM2ATGSDWNSG5Q2LUE/action/replication_record"}},"created_at":"2026-07-03T01:17:43.000474+00:00","updated_at":"2026-07-03T01:17:43.000474+00:00"}