{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6HC2GQMB76VQKFTL5MUSENFUUX","short_pith_number":"pith:6HC2GQMB","schema_version":"1.0","canonical_sha256":"f1c5a34181ffab05166beb292234b4a5e844b97fb57f029b1e17f115cdfd2298","source":{"kind":"arxiv","id":"2305.03101","version":1},"attestation_state":"computed","paper":{"title":"Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Anna Y. Sun, Hirofumi Inaguma, Juan Pino, Ning Dong, Paden D. Tomasello, Xinyue Chen, Xutai Ma, Yun Tang","submitted_at":"2023-05-04T18:34:50Z","abstract_excerpt":"Transducer and Attention based Encoder-Decoder (AED) are two widely used frameworks for speech-to-text tasks. They are designed for different purposes and each has its own benefits and drawbacks for speech-to-text tasks. In order to leverage strengths of both modeling methods, we propose a solution by combining Transducer and Attention based Encoder-Decoder (TAED) for speech-to-text tasks. The new method leverages AED's strength in non-monotonic sequence to sequence learning while retaining Transducer's streaming property. In the proposed framework, Transducer and AED share the same speech enc"},"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":"2305.03101","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T18:34:50Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d6e9153ebc52c555bcec90db8d5884f57ae48ec48a6b40b9302ec3f315416c18","abstract_canon_sha256":"d2781f0972eef1dc2f88eb9557e083a4a0bc278115bf633c3bb52a312c4fdba5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:11.101204Z","signature_b64":"RpeCJbJgJxPtTugDY5Qhh2CN3kaNNhL/Ka2zcFGwpv2iNEjQkZqit9AmJHYNtJFdP36kSlCK+0IddtKJnX1FDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1c5a34181ffab05166beb292234b4a5e844b97fb57f029b1e17f115cdfd2298","last_reissued_at":"2026-07-05T06:07:11.100728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:11.100728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Anna Y. Sun, Hirofumi Inaguma, Juan Pino, Ning Dong, Paden D. Tomasello, Xinyue Chen, Xutai Ma, Yun Tang","submitted_at":"2023-05-04T18:34:50Z","abstract_excerpt":"Transducer and Attention based Encoder-Decoder (AED) are two widely used frameworks for speech-to-text tasks. They are designed for different purposes and each has its own benefits and drawbacks for speech-to-text tasks. In order to leverage strengths of both modeling methods, we propose a solution by combining Transducer and Attention based Encoder-Decoder (TAED) for speech-to-text tasks. The new method leverages AED's strength in non-monotonic sequence to sequence learning while retaining Transducer's streaming property. In the proposed framework, Transducer and AED share the same speech enc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03101","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/2305.03101/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":"2305.03101","created_at":"2026-07-05T06:07:11.100787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.03101v1","created_at":"2026-07-05T06:07:11.100787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03101","created_at":"2026-07-05T06:07:11.100787+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HC2GQMB76VQ","created_at":"2026-07-05T06:07:11.100787+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HC2GQMB76VQKFTL","created_at":"2026-07-05T06:07:11.100787+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HC2GQMB","created_at":"2026-07-05T06:07:11.100787+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08486","citing_title":"TRADE: Transducer-Augmented Decoder for Speech LLM","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6HC2GQMB76VQKFTL5MUSENFUUX","json":"https://pith.science/pith/6HC2GQMB76VQKFTL5MUSENFUUX.json","graph_json":"https://pith.science/api/pith-number/6HC2GQMB76VQKFTL5MUSENFUUX/graph.json","events_json":"https://pith.science/api/pith-number/6HC2GQMB76VQKFTL5MUSENFUUX/events.json","paper":"https://pith.science/paper/6HC2GQMB"},"agent_actions":{"view_html":"https://pith.science/pith/6HC2GQMB76VQKFTL5MUSENFUUX","download_json":"https://pith.science/pith/6HC2GQMB76VQKFTL5MUSENFUUX.json","view_paper":"https://pith.science/paper/6HC2GQMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.03101&json=true","fetch_graph":"https://pith.science/api/pith-number/6HC2GQMB76VQKFTL5MUSENFUUX/graph.json","fetch_events":"https://pith.science/api/pith-number/6HC2GQMB76VQKFTL5MUSENFUUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HC2GQMB76VQKFTL5MUSENFUUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HC2GQMB76VQKFTL5MUSENFUUX/action/storage_attestation","attest_author":"https://pith.science/pith/6HC2GQMB76VQKFTL5MUSENFUUX/action/author_attestation","sign_citation":"https://pith.science/pith/6HC2GQMB76VQKFTL5MUSENFUUX/action/citation_signature","submit_replication":"https://pith.science/pith/6HC2GQMB76VQKFTL5MUSENFUUX/action/replication_record"}},"created_at":"2026-07-05T06:07:11.100787+00:00","updated_at":"2026-07-05T06:07:11.100787+00:00"}