{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VSBLV4QXIJP2XC3KG32AZS6ZWJ","short_pith_number":"pith:VSBLV4QX","schema_version":"1.0","canonical_sha256":"ac82baf217425fab8b6a36f40ccbd9b278914c6e3b77acccb178462c22106de3","source":{"kind":"arxiv","id":"2309.09413","version":1},"attestation_state":"computed","paper":{"title":"Are Soft Prompts Good Zero-shot Learners for Speech Recognition?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Ma, Chongjia Ni, Chong Zhang, Dianwen Ng, Eng Siong Chng, Fabian Ritter-Gutierrez, Ruixi Zhang, Shengkui Zhao, Trung Hieu Nguyen, Yukun Ma","submitted_at":"2023-09-18T01:00:40Z","abstract_excerpt":"Large self-supervised pre-trained speech models require computationally expensive fine-tuning for downstream tasks. Soft prompt tuning offers a simple parameter-efficient alternative by utilizing minimal soft prompt guidance, enhancing portability while also maintaining competitive performance. However, not many people understand how and why this is so. In this study, we aim to deepen our understanding of this emerging method by investigating the role of soft prompts in automatic speech recognition (ASR). Our findings highlight their role as zero-shot learners in improving ASR performance but "},"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":"2309.09413","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-18T01:00:40Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"9024262971af03a81def6a18686bbd42ff231812dc2ac7c03d453987ca6a224e","abstract_canon_sha256":"5629fd27fd0772f1a3502cbee6edb656f1577f7458b8f293a2087f8d7beceace"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:38.720082Z","signature_b64":"vxMTlH7RtStEWMP1GV7RnP68X1NENglU+rfwOmH+fQ0IiGmFQjCj8pyJWC7AoPfZ8zjMDazfJD4DKmMsx+/9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac82baf217425fab8b6a36f40ccbd9b278914c6e3b77acccb178462c22106de3","last_reissued_at":"2026-07-05T06:51:38.719634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:38.719634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Soft Prompts Good Zero-shot Learners for Speech Recognition?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Ma, Chongjia Ni, Chong Zhang, Dianwen Ng, Eng Siong Chng, Fabian Ritter-Gutierrez, Ruixi Zhang, Shengkui Zhao, Trung Hieu Nguyen, Yukun Ma","submitted_at":"2023-09-18T01:00:40Z","abstract_excerpt":"Large self-supervised pre-trained speech models require computationally expensive fine-tuning for downstream tasks. Soft prompt tuning offers a simple parameter-efficient alternative by utilizing minimal soft prompt guidance, enhancing portability while also maintaining competitive performance. However, not many people understand how and why this is so. In this study, we aim to deepen our understanding of this emerging method by investigating the role of soft prompts in automatic speech recognition (ASR). Our findings highlight their role as zero-shot learners in improving ASR performance but "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09413","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/2309.09413/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":"2309.09413","created_at":"2026-07-05T06:51:38.719700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09413v1","created_at":"2026-07-05T06:51:38.719700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09413","created_at":"2026-07-05T06:51:38.719700+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSBLV4QXIJP2","created_at":"2026-07-05T06:51:38.719700+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSBLV4QXIJP2XC3K","created_at":"2026-07-05T06:51:38.719700+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSBLV4QX","created_at":"2026-07-05T06:51:38.719700+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/VSBLV4QXIJP2XC3KG32AZS6ZWJ","json":"https://pith.science/pith/VSBLV4QXIJP2XC3KG32AZS6ZWJ.json","graph_json":"https://pith.science/api/pith-number/VSBLV4QXIJP2XC3KG32AZS6ZWJ/graph.json","events_json":"https://pith.science/api/pith-number/VSBLV4QXIJP2XC3KG32AZS6ZWJ/events.json","paper":"https://pith.science/paper/VSBLV4QX"},"agent_actions":{"view_html":"https://pith.science/pith/VSBLV4QXIJP2XC3KG32AZS6ZWJ","download_json":"https://pith.science/pith/VSBLV4QXIJP2XC3KG32AZS6ZWJ.json","view_paper":"https://pith.science/paper/VSBLV4QX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09413&json=true","fetch_graph":"https://pith.science/api/pith-number/VSBLV4QXIJP2XC3KG32AZS6ZWJ/graph.json","fetch_events":"https://pith.science/api/pith-number/VSBLV4QXIJP2XC3KG32AZS6ZWJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSBLV4QXIJP2XC3KG32AZS6ZWJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSBLV4QXIJP2XC3KG32AZS6ZWJ/action/storage_attestation","attest_author":"https://pith.science/pith/VSBLV4QXIJP2XC3KG32AZS6ZWJ/action/author_attestation","sign_citation":"https://pith.science/pith/VSBLV4QXIJP2XC3KG32AZS6ZWJ/action/citation_signature","submit_replication":"https://pith.science/pith/VSBLV4QXIJP2XC3KG32AZS6ZWJ/action/replication_record"}},"created_at":"2026-07-05T06:51:38.719700+00:00","updated_at":"2026-07-05T06:51:38.719700+00:00"}