{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5BYG3A6UBNASCEHW4ZLI2RVRNS","short_pith_number":"pith:5BYG3A6U","schema_version":"1.0","canonical_sha256":"e8706d83d40b412110f6e6568d46b16c899f664df3c4227dd8ac204c2b86e176","source":{"kind":"arxiv","id":"1811.02775","version":1},"attestation_state":"computed","paper":{"title":"Improved Audio Embeddings by Adjacency-Based Clustering with Applications in Spoken Term Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hung-yi Lee, Lin-shan Lee, Sung-Feng Huang, Yi-Chen Chen","submitted_at":"2018-11-07T06:18:14Z","abstract_excerpt":"Embedding audio signal segments into vectors with fixed dimensionality is attractive because all following processing will be easier and more efficient, for example modeling, classifying or indexing. Audio Word2Vec previously proposed was shown to be able to represent audio segments for spoken words as such vectors carrying information about the phonetic structures of the signal segments. However, each linguistic unit (word, syllable, phoneme in text form) corresponds to unlimited number of audio segments with vector representations inevitably spread over the embedding space, which causes some"},"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":"1811.02775","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-07T06:18:14Z","cross_cats_sorted":[],"title_canon_sha256":"663ea8e215fb5374145652ce39e037396a72baa5febc16bd4a65a8a8e87a5c83","abstract_canon_sha256":"f29109da2924f57f1c49010ba062c7735bff82b6ab02ae4d23d6f65a4e52906b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:20.837712Z","signature_b64":"H2/Q91zCiGNS3IbvLLeRZC0/Tu6KndnpKj5TrWk14QFlLsyI/r4xIv63E3133RKhH3pKwR12WrbVVlevx/f5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8706d83d40b412110f6e6568d46b16c899f664df3c4227dd8ac204c2b86e176","last_reissued_at":"2026-05-18T00:01:20.837028Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:20.837028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Audio Embeddings by Adjacency-Based Clustering with Applications in Spoken Term Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hung-yi Lee, Lin-shan Lee, Sung-Feng Huang, Yi-Chen Chen","submitted_at":"2018-11-07T06:18:14Z","abstract_excerpt":"Embedding audio signal segments into vectors with fixed dimensionality is attractive because all following processing will be easier and more efficient, for example modeling, classifying or indexing. Audio Word2Vec previously proposed was shown to be able to represent audio segments for spoken words as such vectors carrying information about the phonetic structures of the signal segments. However, each linguistic unit (word, syllable, phoneme in text form) corresponds to unlimited number of audio segments with vector representations inevitably spread over the embedding space, which causes some"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02775","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":"1811.02775","created_at":"2026-05-18T00:01:20.837119+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.02775v1","created_at":"2026-05-18T00:01:20.837119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02775","created_at":"2026-05-18T00:01:20.837119+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BYG3A6UBNAS","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BYG3A6UBNASCEHW","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BYG3A6U","created_at":"2026-05-18T12:32:08.215937+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/5BYG3A6UBNASCEHW4ZLI2RVRNS","json":"https://pith.science/pith/5BYG3A6UBNASCEHW4ZLI2RVRNS.json","graph_json":"https://pith.science/api/pith-number/5BYG3A6UBNASCEHW4ZLI2RVRNS/graph.json","events_json":"https://pith.science/api/pith-number/5BYG3A6UBNASCEHW4ZLI2RVRNS/events.json","paper":"https://pith.science/paper/5BYG3A6U"},"agent_actions":{"view_html":"https://pith.science/pith/5BYG3A6UBNASCEHW4ZLI2RVRNS","download_json":"https://pith.science/pith/5BYG3A6UBNASCEHW4ZLI2RVRNS.json","view_paper":"https://pith.science/paper/5BYG3A6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.02775&json=true","fetch_graph":"https://pith.science/api/pith-number/5BYG3A6UBNASCEHW4ZLI2RVRNS/graph.json","fetch_events":"https://pith.science/api/pith-number/5BYG3A6UBNASCEHW4ZLI2RVRNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BYG3A6UBNASCEHW4ZLI2RVRNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BYG3A6UBNASCEHW4ZLI2RVRNS/action/storage_attestation","attest_author":"https://pith.science/pith/5BYG3A6UBNASCEHW4ZLI2RVRNS/action/author_attestation","sign_citation":"https://pith.science/pith/5BYG3A6UBNASCEHW4ZLI2RVRNS/action/citation_signature","submit_replication":"https://pith.science/pith/5BYG3A6UBNASCEHW4ZLI2RVRNS/action/replication_record"}},"created_at":"2026-05-18T00:01:20.837119+00:00","updated_at":"2026-05-18T00:01:20.837119+00:00"}