{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IKMC6TNIQRV7D7RN7CFEFTHQAI","short_pith_number":"pith:IKMC6TNI","schema_version":"1.0","canonical_sha256":"42982f4da8846bf1fe2df88a42ccf00201d275a0f5432a2bcb389b33c91b242e","source":{"kind":"arxiv","id":"2012.02221","version":1},"attestation_state":"computed","paper":{"title":"A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Herman Kamper, Karen Livescu, Puyuan Peng","submitted_at":"2020-12-03T19:24:42Z","abstract_excerpt":"We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and zero-resource languages. Our model, which we refer to as a maximal sampling correspondence variational autoencoder (MCVAE), is a recurrent neural network (RNN) trained with a novel self-supervised correspondence loss that encourages consistency between embeddings of different instances of the same word. Our training scheme improves on previous correspondence tra"},"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":"2012.02221","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-12-03T19:24:42Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"dde07019a57150c8c454d070940ce9d1fa529ae00e5d5f25df7fc68e9898e512","abstract_canon_sha256":"98a32b9fc0de2d02a24dc58266352e61c4b37e479c2eade16cdb68ec5cde1d64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:57.286417Z","signature_b64":"cbW1el5SaLeoV7yutiacpBLKDYleX+iFsbB9wSgn895Kt4OMnwFJwZZHYuZI2FKHFWScJzEs/R9V9vE8XwOcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42982f4da8846bf1fe2df88a42ccf00201d275a0f5432a2bcb389b33c91b242e","last_reissued_at":"2026-07-05T01:56:57.285911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:57.285911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Herman Kamper, Karen Livescu, Puyuan Peng","submitted_at":"2020-12-03T19:24:42Z","abstract_excerpt":"We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and zero-resource languages. Our model, which we refer to as a maximal sampling correspondence variational autoencoder (MCVAE), is a recurrent neural network (RNN) trained with a novel self-supervised correspondence loss that encourages consistency between embeddings of different instances of the same word. Our training scheme improves on previous correspondence tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02221","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/2012.02221/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":"2012.02221","created_at":"2026-07-05T01:56:57.285972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.02221v1","created_at":"2026-07-05T01:56:57.285972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02221","created_at":"2026-07-05T01:56:57.285972+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKMC6TNIQRV7","created_at":"2026-07-05T01:56:57.285972+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKMC6TNIQRV7D7RN","created_at":"2026-07-05T01:56:57.285972+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKMC6TNI","created_at":"2026-07-05T01:56:57.285972+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/IKMC6TNIQRV7D7RN7CFEFTHQAI","json":"https://pith.science/pith/IKMC6TNIQRV7D7RN7CFEFTHQAI.json","graph_json":"https://pith.science/api/pith-number/IKMC6TNIQRV7D7RN7CFEFTHQAI/graph.json","events_json":"https://pith.science/api/pith-number/IKMC6TNIQRV7D7RN7CFEFTHQAI/events.json","paper":"https://pith.science/paper/IKMC6TNI"},"agent_actions":{"view_html":"https://pith.science/pith/IKMC6TNIQRV7D7RN7CFEFTHQAI","download_json":"https://pith.science/pith/IKMC6TNIQRV7D7RN7CFEFTHQAI.json","view_paper":"https://pith.science/paper/IKMC6TNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.02221&json=true","fetch_graph":"https://pith.science/api/pith-number/IKMC6TNIQRV7D7RN7CFEFTHQAI/graph.json","fetch_events":"https://pith.science/api/pith-number/IKMC6TNIQRV7D7RN7CFEFTHQAI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKMC6TNIQRV7D7RN7CFEFTHQAI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKMC6TNIQRV7D7RN7CFEFTHQAI/action/storage_attestation","attest_author":"https://pith.science/pith/IKMC6TNIQRV7D7RN7CFEFTHQAI/action/author_attestation","sign_citation":"https://pith.science/pith/IKMC6TNIQRV7D7RN7CFEFTHQAI/action/citation_signature","submit_replication":"https://pith.science/pith/IKMC6TNIQRV7D7RN7CFEFTHQAI/action/replication_record"}},"created_at":"2026-07-05T01:56:57.285972+00:00","updated_at":"2026-07-05T01:56:57.285972+00:00"}