{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VH2PL63WMY2UFOXANYEOS6FWNO","short_pith_number":"pith:VH2PL63W","schema_version":"1.0","canonical_sha256":"a9f4f5fb76663542bae06e08e978b66bbe4abe8d53ab895f0d83b1ecf5ec8b05","source":{"kind":"arxiv","id":"2209.08326","version":1},"attestation_state":"computed","paper":{"title":"Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Cheng Yi, Hao Ni, Jie Li, Kaituo Xu, Wenjing Han, Xiaorui Wang, Ye Bai, Zhuo Zhang","submitted_at":"2022-09-17T13:22:19Z","abstract_excerpt":"While transformers and their variant conformers show promising performance in speech recognition, the parameterized property leads to much memory cost during training and inference. Some works use cross-layer weight-sharing to reduce the parameters of the model. However, the inevitable loss of capacity harms the model performance. To address this issue, this paper proposes a parameter-efficient conformer via sharing sparsely-gated experts. Specifically, we use sparsely-gated mixture-of-experts (MoE) to extend the capacity of a conformer block without increasing computation. Then, the parameter"},"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":"2209.08326","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-09-17T13:22:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9022e1067b6dabb5066037655e9c14d3c071df7a10bf27032edb9afe3060af2f","abstract_canon_sha256":"f26c6fb4ca8ce6d7a6b44254aa77c6431ba7472d96b05441b4896daf2269183c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:20.022862Z","signature_b64":"corlSAYTdtSG/6NH9dU0H6KiZHPqyGfKG2+XRgH6+xWOXkb7eVEdpn/GknZb/J4CJcHsCkDDFn50WRVtZp/WDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9f4f5fb76663542bae06e08e978b66bbe4abe8d53ab895f0d83b1ecf5ec8b05","last_reissued_at":"2026-07-05T04:58:20.022526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:20.022526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Cheng Yi, Hao Ni, Jie Li, Kaituo Xu, Wenjing Han, Xiaorui Wang, Ye Bai, Zhuo Zhang","submitted_at":"2022-09-17T13:22:19Z","abstract_excerpt":"While transformers and their variant conformers show promising performance in speech recognition, the parameterized property leads to much memory cost during training and inference. Some works use cross-layer weight-sharing to reduce the parameters of the model. However, the inevitable loss of capacity harms the model performance. To address this issue, this paper proposes a parameter-efficient conformer via sharing sparsely-gated experts. Specifically, we use sparsely-gated mixture-of-experts (MoE) to extend the capacity of a conformer block without increasing computation. Then, the parameter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08326","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/2209.08326/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":"2209.08326","created_at":"2026-07-05T04:58:20.022582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.08326v1","created_at":"2026-07-05T04:58:20.022582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08326","created_at":"2026-07-05T04:58:20.022582+00:00"},{"alias_kind":"pith_short_12","alias_value":"VH2PL63WMY2U","created_at":"2026-07-05T04:58:20.022582+00:00"},{"alias_kind":"pith_short_16","alias_value":"VH2PL63WMY2UFOXA","created_at":"2026-07-05T04:58:20.022582+00:00"},{"alias_kind":"pith_short_8","alias_value":"VH2PL63W","created_at":"2026-07-05T04:58:20.022582+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/VH2PL63WMY2UFOXANYEOS6FWNO","json":"https://pith.science/pith/VH2PL63WMY2UFOXANYEOS6FWNO.json","graph_json":"https://pith.science/api/pith-number/VH2PL63WMY2UFOXANYEOS6FWNO/graph.json","events_json":"https://pith.science/api/pith-number/VH2PL63WMY2UFOXANYEOS6FWNO/events.json","paper":"https://pith.science/paper/VH2PL63W"},"agent_actions":{"view_html":"https://pith.science/pith/VH2PL63WMY2UFOXANYEOS6FWNO","download_json":"https://pith.science/pith/VH2PL63WMY2UFOXANYEOS6FWNO.json","view_paper":"https://pith.science/paper/VH2PL63W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.08326&json=true","fetch_graph":"https://pith.science/api/pith-number/VH2PL63WMY2UFOXANYEOS6FWNO/graph.json","fetch_events":"https://pith.science/api/pith-number/VH2PL63WMY2UFOXANYEOS6FWNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VH2PL63WMY2UFOXANYEOS6FWNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VH2PL63WMY2UFOXANYEOS6FWNO/action/storage_attestation","attest_author":"https://pith.science/pith/VH2PL63WMY2UFOXANYEOS6FWNO/action/author_attestation","sign_citation":"https://pith.science/pith/VH2PL63WMY2UFOXANYEOS6FWNO/action/citation_signature","submit_replication":"https://pith.science/pith/VH2PL63WMY2UFOXANYEOS6FWNO/action/replication_record"}},"created_at":"2026-07-05T04:58:20.022582+00:00","updated_at":"2026-07-05T04:58:20.022582+00:00"}