{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7UQVQXXMWRKWGUMPKJVFKWDFRY","short_pith_number":"pith:7UQVQXXM","schema_version":"1.0","canonical_sha256":"fd21585eecb45563518f526a5558658e318f3930c67cc5bdc57e58f703da9f39","source":{"kind":"arxiv","id":"2204.01235","version":2},"attestation_state":"computed","paper":{"title":"An Analysis of Semantically-Aligned Speech-Text Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ivan Kukanov, Muhammad Huzaifah","submitted_at":"2022-04-04T04:50:32Z","abstract_excerpt":"Embeddings play an important role in end-to-end solutions for multi-modal language processing problems. Although there has been some effort to understand the properties of single-modality embedding spaces, particularly that of text, their cross-modal counterparts are less understood. In this work, we study some intrinsic properties of a joint speech-text embedding space, constructed by minimizing the distance between paired utterance and transcription inputs in a teacher-student model setup, that are informative for several prominent use cases. We found that incorporating automatic speech reco"},"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":"2204.01235","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-04T04:50:32Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"b6ecd12c81f72ab6b1a628099316a5fb94fe94055c8c78aa98fc6daa6dc78b12","abstract_canon_sha256":"3a7cf25aa4f1b79b923ba9683efe02b2c64d84c2f7d305076995306bec0df181"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:14.694335Z","signature_b64":"VY0dZGdM0m5MZaJt2wplzXgFSi4EnvnRHDtnXLKxFeDwxj15Aa8B77mxYcY+y2+r1Zm31H35aSUzWEdXuymYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd21585eecb45563518f526a5558658e318f3930c67cc5bdc57e58f703da9f39","last_reissued_at":"2026-07-05T05:34:14.693941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:14.693941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Analysis of Semantically-Aligned Speech-Text Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ivan Kukanov, Muhammad Huzaifah","submitted_at":"2022-04-04T04:50:32Z","abstract_excerpt":"Embeddings play an important role in end-to-end solutions for multi-modal language processing problems. Although there has been some effort to understand the properties of single-modality embedding spaces, particularly that of text, their cross-modal counterparts are less understood. In this work, we study some intrinsic properties of a joint speech-text embedding space, constructed by minimizing the distance between paired utterance and transcription inputs in a teacher-student model setup, that are informative for several prominent use cases. We found that incorporating automatic speech reco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.01235","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/2204.01235/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":"2204.01235","created_at":"2026-07-05T05:34:14.694005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.01235v2","created_at":"2026-07-05T05:34:14.694005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.01235","created_at":"2026-07-05T05:34:14.694005+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UQVQXXMWRKW","created_at":"2026-07-05T05:34:14.694005+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UQVQXXMWRKWGUMP","created_at":"2026-07-05T05:34:14.694005+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UQVQXXM","created_at":"2026-07-05T05:34:14.694005+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/7UQVQXXMWRKWGUMPKJVFKWDFRY","json":"https://pith.science/pith/7UQVQXXMWRKWGUMPKJVFKWDFRY.json","graph_json":"https://pith.science/api/pith-number/7UQVQXXMWRKWGUMPKJVFKWDFRY/graph.json","events_json":"https://pith.science/api/pith-number/7UQVQXXMWRKWGUMPKJVFKWDFRY/events.json","paper":"https://pith.science/paper/7UQVQXXM"},"agent_actions":{"view_html":"https://pith.science/pith/7UQVQXXMWRKWGUMPKJVFKWDFRY","download_json":"https://pith.science/pith/7UQVQXXMWRKWGUMPKJVFKWDFRY.json","view_paper":"https://pith.science/paper/7UQVQXXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.01235&json=true","fetch_graph":"https://pith.science/api/pith-number/7UQVQXXMWRKWGUMPKJVFKWDFRY/graph.json","fetch_events":"https://pith.science/api/pith-number/7UQVQXXMWRKWGUMPKJVFKWDFRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UQVQXXMWRKWGUMPKJVFKWDFRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UQVQXXMWRKWGUMPKJVFKWDFRY/action/storage_attestation","attest_author":"https://pith.science/pith/7UQVQXXMWRKWGUMPKJVFKWDFRY/action/author_attestation","sign_citation":"https://pith.science/pith/7UQVQXXMWRKWGUMPKJVFKWDFRY/action/citation_signature","submit_replication":"https://pith.science/pith/7UQVQXXMWRKWGUMPKJVFKWDFRY/action/replication_record"}},"created_at":"2026-07-05T05:34:14.694005+00:00","updated_at":"2026-07-05T05:34:14.694005+00:00"}