{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5U3GCXZAMORDMEWYL3XNA4PZOL","short_pith_number":"pith:5U3GCXZA","schema_version":"1.0","canonical_sha256":"ed36615f2063a23612d85eeed071f972e9acd825afbf447ac767d4cf6ba2218c","source":{"kind":"arxiv","id":"2407.18223","version":2},"attestation_state":"computed","paper":{"title":"Reshape Dimensions Network for Speaker Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Andrei Balykin, Anton Okhotnikov, Ivan Yakovlev, Nikita Torgashov, Pavel Malov, Rostislav Makarov","submitted_at":"2024-07-25T17:39:34Z","abstract_excerpt":"In this paper, we present Reshape Dimensions Network (ReDimNet), a novel neural network architecture for extracting utterance-level speaker representations. Our approach leverages dimensionality reshaping of 2D feature maps to 1D signal representation and vice versa, enabling the joint usage of 1D and 2D blocks. We propose an original network topology that preserves the volume of channel-timestep-frequency outputs of 1D and 2D blocks, facilitating efficient residual feature maps aggregation. Moreover, ReDimNet is efficiently scalable, and we introduce a range of model sizes, varying from 1 to "},"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":"2407.18223","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-25T17:39:34Z","cross_cats_sorted":[],"title_canon_sha256":"93d6521c05e12fe23aa39e00a4813da6a81021edc0836b6759580013f39d2e03","abstract_canon_sha256":"9d9adefb012e92da3371bd18c7016ed72b38604b31f584cc192c92002565105d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:28.206355Z","signature_b64":"9s8l9JYCHbVXgHoS/T+Jg1GcS6k80QD44eMImrCTbLuRmvMnPqWYmhZjBFBMqquNHvAwgb0Tn2qJ21f1UjetCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed36615f2063a23612d85eeed071f972e9acd825afbf447ac767d4cf6ba2218c","last_reissued_at":"2026-07-05T09:11:28.205850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:28.205850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reshape Dimensions Network for Speaker Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Andrei Balykin, Anton Okhotnikov, Ivan Yakovlev, Nikita Torgashov, Pavel Malov, Rostislav Makarov","submitted_at":"2024-07-25T17:39:34Z","abstract_excerpt":"In this paper, we present Reshape Dimensions Network (ReDimNet), a novel neural network architecture for extracting utterance-level speaker representations. Our approach leverages dimensionality reshaping of 2D feature maps to 1D signal representation and vice versa, enabling the joint usage of 1D and 2D blocks. We propose an original network topology that preserves the volume of channel-timestep-frequency outputs of 1D and 2D blocks, facilitating efficient residual feature maps aggregation. Moreover, ReDimNet is efficiently scalable, and we introduce a range of model sizes, varying from 1 to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18223","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/2407.18223/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":"2407.18223","created_at":"2026-07-05T09:11:28.205911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18223v2","created_at":"2026-07-05T09:11:28.205911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18223","created_at":"2026-07-05T09:11:28.205911+00:00"},{"alias_kind":"pith_short_12","alias_value":"5U3GCXZAMORD","created_at":"2026-07-05T09:11:28.205911+00:00"},{"alias_kind":"pith_short_16","alias_value":"5U3GCXZAMORDMEWY","created_at":"2026-07-05T09:11:28.205911+00:00"},{"alias_kind":"pith_short_8","alias_value":"5U3GCXZA","created_at":"2026-07-05T09:11:28.205911+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16276","citing_title":"The SVASR System for Text-dependent Speaker Verification (TdSV) AAIC Challenge 2024","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5U3GCXZAMORDMEWYL3XNA4PZOL","json":"https://pith.science/pith/5U3GCXZAMORDMEWYL3XNA4PZOL.json","graph_json":"https://pith.science/api/pith-number/5U3GCXZAMORDMEWYL3XNA4PZOL/graph.json","events_json":"https://pith.science/api/pith-number/5U3GCXZAMORDMEWYL3XNA4PZOL/events.json","paper":"https://pith.science/paper/5U3GCXZA"},"agent_actions":{"view_html":"https://pith.science/pith/5U3GCXZAMORDMEWYL3XNA4PZOL","download_json":"https://pith.science/pith/5U3GCXZAMORDMEWYL3XNA4PZOL.json","view_paper":"https://pith.science/paper/5U3GCXZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18223&json=true","fetch_graph":"https://pith.science/api/pith-number/5U3GCXZAMORDMEWYL3XNA4PZOL/graph.json","fetch_events":"https://pith.science/api/pith-number/5U3GCXZAMORDMEWYL3XNA4PZOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5U3GCXZAMORDMEWYL3XNA4PZOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5U3GCXZAMORDMEWYL3XNA4PZOL/action/storage_attestation","attest_author":"https://pith.science/pith/5U3GCXZAMORDMEWYL3XNA4PZOL/action/author_attestation","sign_citation":"https://pith.science/pith/5U3GCXZAMORDMEWYL3XNA4PZOL/action/citation_signature","submit_replication":"https://pith.science/pith/5U3GCXZAMORDMEWYL3XNA4PZOL/action/replication_record"}},"created_at":"2026-07-05T09:11:28.205911+00:00","updated_at":"2026-07-05T09:11:28.205911+00:00"}