{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:N2CVCABDXKABVVCCSQSJ4TYB6M","short_pith_number":"pith:N2CVCABD","schema_version":"1.0","canonical_sha256":"6e85510023ba801ad44294249e4f01f336597f4b642439e668c0f69c28f1c0fb","source":{"kind":"arxiv","id":"2101.05056","version":1},"attestation_state":"computed","paper":{"title":"End-to-End Speaker Height and age estimation using Attention Mechanism with LSTM-RNN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SD","authors_text":"Eng Siong Chng, Manav Kaushik, Van Tung Pham","submitted_at":"2021-01-13T13:41:18Z","abstract_excerpt":"Automatic height and age estimation of speakers using acoustic features is widely used for the purpose of human-computer interaction, forensics, etc. In this work, we propose a novel approach of using attention mechanism to build an end-to-end architecture for height and age estimation. The attention mechanism is combined with Long Short-Term Memory(LSTM) encoder which is able to capture long-term dependencies in the input acoustic features. We modify the conventionally used Attention -- which calculates context vectors the sum of attention only across timeframes -- by introducing a modified c"},"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":"2101.05056","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-01-13T13:41:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d373ff5b7d57481bbd34e94f857df472757c399354d6347a33f91c00539d00b8","abstract_canon_sha256":"1f2990a6f61e9ad0a07bf8a655d1a7188830c99dbe3a8ea2d7469e5ac785fc20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:06:37.561207Z","signature_b64":"BA8UoLQANP3hiLKVtH/n+16P+D3fQX8+BMsoBny0KPdIsY2lmwlpbORPSZYtYMWeIUBlW6F79qg5EttVRX/mCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e85510023ba801ad44294249e4f01f336597f4b642439e668c0f69c28f1c0fb","last_reissued_at":"2026-07-05T02:06:37.560712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:06:37.560712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Speaker Height and age estimation using Attention Mechanism with LSTM-RNN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SD","authors_text":"Eng Siong Chng, Manav Kaushik, Van Tung Pham","submitted_at":"2021-01-13T13:41:18Z","abstract_excerpt":"Automatic height and age estimation of speakers using acoustic features is widely used for the purpose of human-computer interaction, forensics, etc. In this work, we propose a novel approach of using attention mechanism to build an end-to-end architecture for height and age estimation. The attention mechanism is combined with Long Short-Term Memory(LSTM) encoder which is able to capture long-term dependencies in the input acoustic features. We modify the conventionally used Attention -- which calculates context vectors the sum of attention only across timeframes -- by introducing a modified c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.05056","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/2101.05056/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":"2101.05056","created_at":"2026-07-05T02:06:37.560769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.05056v1","created_at":"2026-07-05T02:06:37.560769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.05056","created_at":"2026-07-05T02:06:37.560769+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2CVCABDXKAB","created_at":"2026-07-05T02:06:37.560769+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2CVCABDXKABVVCC","created_at":"2026-07-05T02:06:37.560769+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2CVCABD","created_at":"2026-07-05T02:06:37.560769+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/N2CVCABDXKABVVCCSQSJ4TYB6M","json":"https://pith.science/pith/N2CVCABDXKABVVCCSQSJ4TYB6M.json","graph_json":"https://pith.science/api/pith-number/N2CVCABDXKABVVCCSQSJ4TYB6M/graph.json","events_json":"https://pith.science/api/pith-number/N2CVCABDXKABVVCCSQSJ4TYB6M/events.json","paper":"https://pith.science/paper/N2CVCABD"},"agent_actions":{"view_html":"https://pith.science/pith/N2CVCABDXKABVVCCSQSJ4TYB6M","download_json":"https://pith.science/pith/N2CVCABDXKABVVCCSQSJ4TYB6M.json","view_paper":"https://pith.science/paper/N2CVCABD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.05056&json=true","fetch_graph":"https://pith.science/api/pith-number/N2CVCABDXKABVVCCSQSJ4TYB6M/graph.json","fetch_events":"https://pith.science/api/pith-number/N2CVCABDXKABVVCCSQSJ4TYB6M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2CVCABDXKABVVCCSQSJ4TYB6M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2CVCABDXKABVVCCSQSJ4TYB6M/action/storage_attestation","attest_author":"https://pith.science/pith/N2CVCABDXKABVVCCSQSJ4TYB6M/action/author_attestation","sign_citation":"https://pith.science/pith/N2CVCABDXKABVVCCSQSJ4TYB6M/action/citation_signature","submit_replication":"https://pith.science/pith/N2CVCABDXKABVVCCSQSJ4TYB6M/action/replication_record"}},"created_at":"2026-07-05T02:06:37.560769+00:00","updated_at":"2026-07-05T02:06:37.560769+00:00"}