{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NWKPHIRAB7W3CDCDS2MWQF3QTS","short_pith_number":"pith:NWKPHIRA","schema_version":"1.0","canonical_sha256":"6d94f3a2200fedb10c4396996817709cba1b82a68534afa120894bf9eabecb33","source":{"kind":"arxiv","id":"2210.00705","version":2},"attestation_state":"computed","paper":{"title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"David Harwath, Heng-Jui Chang, Hsuan-Fu Wang, Hung-yi Lee, Layne Berry, Yi-Jen Shih","submitted_at":"2022-10-03T04:15:36Z","abstract_excerpt":"Data-driven speech processing models usually perform well with a large amount of text supervision, but collecting transcribed speech data is costly. Therefore, we propose SpeechCLIP, a novel framework bridging speech and text through images to enhance speech models without transcriptions. We leverage state-of-the-art pre-trained HuBERT and CLIP, aligning them via paired images and spoken captions with minimal fine-tuning. SpeechCLIP outperforms prior state-of-the-art on image-speech retrieval and performs zero-shot speech-text retrieval without direct supervision from transcriptions. Moreover,"},"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":"2210.00705","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-03T04:15:36Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"1afb06f70a9f61b4d3a8a6203d80d4c50981b6432ef095d101d74512cc56f606","abstract_canon_sha256":"809b8958bbeaaf17882b2adb784f2f09d7ed255a767fb9e1228306dfb2b35346"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:15.790866Z","signature_b64":"W6+IKRu/3mUSQibU7mQVc0ckk/7xssMgggiaY+zHHLLHLylYrTKGQxMseZK2ZO8YD4BfE/ZDJiFg1jWRrDPcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d94f3a2200fedb10c4396996817709cba1b82a68534afa120894bf9eabecb33","last_reissued_at":"2026-07-05T05:10:15.790472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:15.790472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"David Harwath, Heng-Jui Chang, Hsuan-Fu Wang, Hung-yi Lee, Layne Berry, Yi-Jen Shih","submitted_at":"2022-10-03T04:15:36Z","abstract_excerpt":"Data-driven speech processing models usually perform well with a large amount of text supervision, but collecting transcribed speech data is costly. Therefore, we propose SpeechCLIP, a novel framework bridging speech and text through images to enhance speech models without transcriptions. We leverage state-of-the-art pre-trained HuBERT and CLIP, aligning them via paired images and spoken captions with minimal fine-tuning. SpeechCLIP outperforms prior state-of-the-art on image-speech retrieval and performs zero-shot speech-text retrieval without direct supervision from transcriptions. Moreover,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00705","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/2210.00705/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":"2210.00705","created_at":"2026-07-05T05:10:15.790535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00705v2","created_at":"2026-07-05T05:10:15.790535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00705","created_at":"2026-07-05T05:10:15.790535+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWKPHIRAB7W3","created_at":"2026-07-05T05:10:15.790535+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWKPHIRAB7W3CDCD","created_at":"2026-07-05T05:10:15.790535+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWKPHIRA","created_at":"2026-07-05T05:10:15.790535+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/NWKPHIRAB7W3CDCDS2MWQF3QTS","json":"https://pith.science/pith/NWKPHIRAB7W3CDCDS2MWQF3QTS.json","graph_json":"https://pith.science/api/pith-number/NWKPHIRAB7W3CDCDS2MWQF3QTS/graph.json","events_json":"https://pith.science/api/pith-number/NWKPHIRAB7W3CDCDS2MWQF3QTS/events.json","paper":"https://pith.science/paper/NWKPHIRA"},"agent_actions":{"view_html":"https://pith.science/pith/NWKPHIRAB7W3CDCDS2MWQF3QTS","download_json":"https://pith.science/pith/NWKPHIRAB7W3CDCDS2MWQF3QTS.json","view_paper":"https://pith.science/paper/NWKPHIRA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00705&json=true","fetch_graph":"https://pith.science/api/pith-number/NWKPHIRAB7W3CDCDS2MWQF3QTS/graph.json","fetch_events":"https://pith.science/api/pith-number/NWKPHIRAB7W3CDCDS2MWQF3QTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWKPHIRAB7W3CDCDS2MWQF3QTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWKPHIRAB7W3CDCDS2MWQF3QTS/action/storage_attestation","attest_author":"https://pith.science/pith/NWKPHIRAB7W3CDCDS2MWQF3QTS/action/author_attestation","sign_citation":"https://pith.science/pith/NWKPHIRAB7W3CDCDS2MWQF3QTS/action/citation_signature","submit_replication":"https://pith.science/pith/NWKPHIRAB7W3CDCDS2MWQF3QTS/action/replication_record"}},"created_at":"2026-07-05T05:10:15.790535+00:00","updated_at":"2026-07-05T05:10:15.790535+00:00"}