{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ALBWGN5TYSUCWMXUJEYAQF7CRN","short_pith_number":"pith:ALBWGN5T","schema_version":"1.0","canonical_sha256":"02c36337b3c4a82b32f449300817e28b463a4b31c40a1db54591c82b25b4da61","source":{"kind":"arxiv","id":"2211.01571","version":2},"attestation_state":"computed","paper":{"title":"Phonetic-assisted Multi-Target Units Modeling for Improving Conformer-Transducer ASR system","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dongxing Xu, Haoran Wei, Li Li, Yanhua Long","submitted_at":"2022-11-03T03:36:51Z","abstract_excerpt":"Exploiting effective target modeling units is very important and has always been a concern in end-to-end automatic speech recognition (ASR). In this work, we propose a phonetic-assisted multi target units (PMU) modeling approach, to enhance the Conformer-Transducer ASR system in a progressive representation learning manner. Specifically, PMU first uses the pronunciation-assisted subword modeling (PASM) and byte pair encoding (BPE) to produce phonetic-induced and text-induced target units separately; Then, three new frameworks are investigated to enhance the acoustic encoder, including a basic "},"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":"2211.01571","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-03T03:36:51Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"a201eafd630551b3e2793be83e763982cf2752b549b1615ee00cca335fe379f9","abstract_canon_sha256":"996b6acadec72d4b26f7565f5c1242da6a8ed741fb7baa3e90222a61209253b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:32.563338Z","signature_b64":"HCeqaq3cPtd/nIjBXO55etCNhYx2Z8231FgCkMP4Rb76jOgy+M7Q1XKTWkfLNcGJYyWbMzXGkYmmfZXajdujCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02c36337b3c4a82b32f449300817e28b463a4b31c40a1db54591c82b25b4da61","last_reissued_at":"2026-07-05T06:28:32.562841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:32.562841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phonetic-assisted Multi-Target Units Modeling for Improving Conformer-Transducer ASR system","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dongxing Xu, Haoran Wei, Li Li, Yanhua Long","submitted_at":"2022-11-03T03:36:51Z","abstract_excerpt":"Exploiting effective target modeling units is very important and has always been a concern in end-to-end automatic speech recognition (ASR). In this work, we propose a phonetic-assisted multi target units (PMU) modeling approach, to enhance the Conformer-Transducer ASR system in a progressive representation learning manner. Specifically, PMU first uses the pronunciation-assisted subword modeling (PASM) and byte pair encoding (BPE) to produce phonetic-induced and text-induced target units separately; Then, three new frameworks are investigated to enhance the acoustic encoder, including a basic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01571","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/2211.01571/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":"2211.01571","created_at":"2026-07-05T06:28:32.562905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.01571v2","created_at":"2026-07-05T06:28:32.562905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01571","created_at":"2026-07-05T06:28:32.562905+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALBWGN5TYSUC","created_at":"2026-07-05T06:28:32.562905+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALBWGN5TYSUCWMXU","created_at":"2026-07-05T06:28:32.562905+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALBWGN5T","created_at":"2026-07-05T06:28:32.562905+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/ALBWGN5TYSUCWMXUJEYAQF7CRN","json":"https://pith.science/pith/ALBWGN5TYSUCWMXUJEYAQF7CRN.json","graph_json":"https://pith.science/api/pith-number/ALBWGN5TYSUCWMXUJEYAQF7CRN/graph.json","events_json":"https://pith.science/api/pith-number/ALBWGN5TYSUCWMXUJEYAQF7CRN/events.json","paper":"https://pith.science/paper/ALBWGN5T"},"agent_actions":{"view_html":"https://pith.science/pith/ALBWGN5TYSUCWMXUJEYAQF7CRN","download_json":"https://pith.science/pith/ALBWGN5TYSUCWMXUJEYAQF7CRN.json","view_paper":"https://pith.science/paper/ALBWGN5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.01571&json=true","fetch_graph":"https://pith.science/api/pith-number/ALBWGN5TYSUCWMXUJEYAQF7CRN/graph.json","fetch_events":"https://pith.science/api/pith-number/ALBWGN5TYSUCWMXUJEYAQF7CRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALBWGN5TYSUCWMXUJEYAQF7CRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALBWGN5TYSUCWMXUJEYAQF7CRN/action/storage_attestation","attest_author":"https://pith.science/pith/ALBWGN5TYSUCWMXUJEYAQF7CRN/action/author_attestation","sign_citation":"https://pith.science/pith/ALBWGN5TYSUCWMXUJEYAQF7CRN/action/citation_signature","submit_replication":"https://pith.science/pith/ALBWGN5TYSUCWMXUJEYAQF7CRN/action/replication_record"}},"created_at":"2026-07-05T06:28:32.562905+00:00","updated_at":"2026-07-05T06:28:32.562905+00:00"}