{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ROICNBXZ5LRYNR6RY4MTU4HRUJ","short_pith_number":"pith:ROICNBXZ","schema_version":"1.0","canonical_sha256":"8b902686f9eae386c7d1c7193a70f1a25fffdf25bd8cc7897fb225a3377bc2a9","source":{"kind":"arxiv","id":"1710.10059","version":2},"attestation_state":"computed","paper":{"title":"Direction of arrival estimation for multiple sound sources using convolutional recurrent neural network","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Archontis Politis, Sharath Adavanne, Tuomas Virtanen","submitted_at":"2017-10-27T10:24:00Z","abstract_excerpt":"This paper proposes a deep neural network for estimating the directions of arrival (DOA) of multiple sound sources. The proposed stacked convolutional and recurrent neural network (DOAnet) generates a spatial pseudo-spectrum (SPS) along with the DOA estimates in both azimuth and elevation. We avoid any explicit feature extraction step by using the magnitudes and phases of the spectrograms of all the channels as input to the network. The proposed DOAnet is evaluated by estimating the DOAs of multiple concurrently present sources in anechoic, matched and unmatched reverberant conditions. The res"},"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":"1710.10059","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2017-10-27T10:24:00Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"082736d1aa797c9a3828e9d00a1f4849e70c898909de0fb9cdcbd855545febb3","abstract_canon_sha256":"05e6815839a912e38ec0d8a7dbdfd3335ac59e7505856e790198db2990305f7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:55.039635Z","signature_b64":"weqqC7KMmYJ//Wj7nfqdG5evdaeE+00r0VeJUD5MVEU30TwdOJ5JmHXAVo/Zzrw3mwyQHBEWc5cutgd3F2rxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b902686f9eae386c7d1c7193a70f1a25fffdf25bd8cc7897fb225a3377bc2a9","last_reissued_at":"2026-05-18T00:08:55.038930Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:55.038930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Direction of arrival estimation for multiple sound sources using convolutional recurrent neural network","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Archontis Politis, Sharath Adavanne, Tuomas Virtanen","submitted_at":"2017-10-27T10:24:00Z","abstract_excerpt":"This paper proposes a deep neural network for estimating the directions of arrival (DOA) of multiple sound sources. The proposed stacked convolutional and recurrent neural network (DOAnet) generates a spatial pseudo-spectrum (SPS) along with the DOA estimates in both azimuth and elevation. We avoid any explicit feature extraction step by using the magnitudes and phases of the spectrograms of all the channels as input to the network. The proposed DOAnet is evaluated by estimating the DOAs of multiple concurrently present sources in anechoic, matched and unmatched reverberant conditions. The res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10059","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":"1710.10059","created_at":"2026-05-18T00:08:55.039040+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.10059v2","created_at":"2026-05-18T00:08:55.039040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10059","created_at":"2026-05-18T00:08:55.039040+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROICNBXZ5LRY","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROICNBXZ5LRYNR6R","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROICNBXZ","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.08968","citing_title":"Mirage: 2D Source Localization Using Microphone Pair Augmentation with Echoes","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROICNBXZ5LRYNR6RY4MTU4HRUJ","json":"https://pith.science/pith/ROICNBXZ5LRYNR6RY4MTU4HRUJ.json","graph_json":"https://pith.science/api/pith-number/ROICNBXZ5LRYNR6RY4MTU4HRUJ/graph.json","events_json":"https://pith.science/api/pith-number/ROICNBXZ5LRYNR6RY4MTU4HRUJ/events.json","paper":"https://pith.science/paper/ROICNBXZ"},"agent_actions":{"view_html":"https://pith.science/pith/ROICNBXZ5LRYNR6RY4MTU4HRUJ","download_json":"https://pith.science/pith/ROICNBXZ5LRYNR6RY4MTU4HRUJ.json","view_paper":"https://pith.science/paper/ROICNBXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.10059&json=true","fetch_graph":"https://pith.science/api/pith-number/ROICNBXZ5LRYNR6RY4MTU4HRUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ROICNBXZ5LRYNR6RY4MTU4HRUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROICNBXZ5LRYNR6RY4MTU4HRUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROICNBXZ5LRYNR6RY4MTU4HRUJ/action/storage_attestation","attest_author":"https://pith.science/pith/ROICNBXZ5LRYNR6RY4MTU4HRUJ/action/author_attestation","sign_citation":"https://pith.science/pith/ROICNBXZ5LRYNR6RY4MTU4HRUJ/action/citation_signature","submit_replication":"https://pith.science/pith/ROICNBXZ5LRYNR6RY4MTU4HRUJ/action/replication_record"}},"created_at":"2026-05-18T00:08:55.039040+00:00","updated_at":"2026-05-18T00:08:55.039040+00:00"}