{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2RS4QZPMB7SQQSIIBBQHFH7OL2","short_pith_number":"pith:2RS4QZPM","schema_version":"1.0","canonical_sha256":"d465c865ec0fe50849080860729fee5e9f20f76ea44b5c8dca5c97ee0156f680","source":{"kind":"arxiv","id":"1711.01515","version":1},"attestation_state":"computed","paper":{"title":"Learning Word Embeddings from Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"James Glass, Yu-An Chung","submitted_at":"2017-11-05T01:36:58Z","abstract_excerpt":"In this paper, we propose a novel deep neural network architecture, Sequence-to-Sequence Audio2Vec, for unsupervised learning of fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain semantic information pertaining to the segments, and are close to other vectors in the embedding space if their corresponding segments are semantically similar. The design of the proposed model is based on the RNN Encoder-Decoder framework, and borrows the methodology of continuous skip-grams for training. The learned vector representations are evaluated on 1"},"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":"1711.01515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-05T01:36:58Z","cross_cats_sorted":[],"title_canon_sha256":"8bae0b2d77b0e4b3821847cd6ad839ec9109ae7096a69cba9e627a3b91954027","abstract_canon_sha256":"22580949fb28833c30f4a04514cf7780107731c8e3c17416a9ab15369f41305d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:17.593045Z","signature_b64":"hOrqzARqn9IwzrLFl4K+2t81Y1cVqG7s0COyBhktfgu/6JF1DAv7D6kFMq7ixtJLVHLvbM5Pm95YrHoxBLn5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d465c865ec0fe50849080860729fee5e9f20f76ea44b5c8dca5c97ee0156f680","last_reissued_at":"2026-05-18T00:31:17.592551Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:17.592551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Word Embeddings from Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"James Glass, Yu-An Chung","submitted_at":"2017-11-05T01:36:58Z","abstract_excerpt":"In this paper, we propose a novel deep neural network architecture, Sequence-to-Sequence Audio2Vec, for unsupervised learning of fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain semantic information pertaining to the segments, and are close to other vectors in the embedding space if their corresponding segments are semantically similar. The design of the proposed model is based on the RNN Encoder-Decoder framework, and borrows the methodology of continuous skip-grams for training. The learned vector representations are evaluated on 1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.01515","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":""},"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":"1711.01515","created_at":"2026-05-18T00:31:17.592622+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.01515v1","created_at":"2026-05-18T00:31:17.592622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.01515","created_at":"2026-05-18T00:31:17.592622+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RS4QZPMB7SQ","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RS4QZPMB7SQQSII","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RS4QZPM","created_at":"2026-05-18T12:30:55.937587+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/2RS4QZPMB7SQQSIIBBQHFH7OL2","json":"https://pith.science/pith/2RS4QZPMB7SQQSIIBBQHFH7OL2.json","graph_json":"https://pith.science/api/pith-number/2RS4QZPMB7SQQSIIBBQHFH7OL2/graph.json","events_json":"https://pith.science/api/pith-number/2RS4QZPMB7SQQSIIBBQHFH7OL2/events.json","paper":"https://pith.science/paper/2RS4QZPM"},"agent_actions":{"view_html":"https://pith.science/pith/2RS4QZPMB7SQQSIIBBQHFH7OL2","download_json":"https://pith.science/pith/2RS4QZPMB7SQQSIIBBQHFH7OL2.json","view_paper":"https://pith.science/paper/2RS4QZPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.01515&json=true","fetch_graph":"https://pith.science/api/pith-number/2RS4QZPMB7SQQSIIBBQHFH7OL2/graph.json","fetch_events":"https://pith.science/api/pith-number/2RS4QZPMB7SQQSIIBBQHFH7OL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RS4QZPMB7SQQSIIBBQHFH7OL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RS4QZPMB7SQQSIIBBQHFH7OL2/action/storage_attestation","attest_author":"https://pith.science/pith/2RS4QZPMB7SQQSIIBBQHFH7OL2/action/author_attestation","sign_citation":"https://pith.science/pith/2RS4QZPMB7SQQSIIBBQHFH7OL2/action/citation_signature","submit_replication":"https://pith.science/pith/2RS4QZPMB7SQQSIIBBQHFH7OL2/action/replication_record"}},"created_at":"2026-05-18T00:31:17.592622+00:00","updated_at":"2026-05-18T00:31:17.592622+00:00"}