{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GKUWYLLAWZN2BM44R5QQP33CYT","short_pith_number":"pith:GKUWYLLA","schema_version":"1.0","canonical_sha256":"32a96c2d60b65ba0b39c8f6107ef62c4d377d0bc39a4532ea04c3dec250f7922","source":{"kind":"arxiv","id":"1910.12977","version":1},"attestation_state":"computed","paper":{"title":"Transformer-Transducer: End-to-End Speech Recognition with Self-Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ching-Feng Yeh, Christian Fuegen, Duc Le, Jay Mahadeokar, Kaustubh Kalgaonkar, Kjell Schubert, Mahaveer Jain, Michael L. Seltzer, Yongqiang Wang","submitted_at":"2019-10-28T21:29:21Z","abstract_excerpt":"We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts. We propose 1) using VGGNet with causal convolution to incorporate positional information and reduce frame rate for efficient inference 2) using truncated self-attention to enable streaming for Transformer and reduce computational complexity. All experiments are conducted on the public LibriSpeech corpus. The proposed Transformer-Transducer outperforms neural "},"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":"1910.12977","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-10-28T21:29:21Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"38095dfddc1f5ed14cc2213e2aba4fd1793f6fb2fb251aefda8da46a09a87412","abstract_canon_sha256":"6395fc2eb395eac875d7a804b3b6a6e848ec6fa66a9760c06ba36eb26f2fdc04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:25.850102Z","signature_b64":"HIUKWzgiN2oWgfQINv0j+na7SstUTNi0f4QjsQK+A6ozEjqgSIN8vw9I2BctAw0IjUbMgvwzpPkJk21YX5rBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32a96c2d60b65ba0b39c8f6107ef62c4d377d0bc39a4532ea04c3dec250f7922","last_reissued_at":"2026-07-05T00:15:25.849608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:25.849608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer-Transducer: End-to-End Speech Recognition with Self-Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ching-Feng Yeh, Christian Fuegen, Duc Le, Jay Mahadeokar, Kaustubh Kalgaonkar, Kjell Schubert, Mahaveer Jain, Michael L. Seltzer, Yongqiang Wang","submitted_at":"2019-10-28T21:29:21Z","abstract_excerpt":"We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts. We propose 1) using VGGNet with causal convolution to incorporate positional information and reduce frame rate for efficient inference 2) using truncated self-attention to enable streaming for Transformer and reduce computational complexity. All experiments are conducted on the public LibriSpeech corpus. The proposed Transformer-Transducer outperforms neural "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.12977","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/1910.12977/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":"1910.12977","created_at":"2026-07-05T00:15:25.849667+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.12977v1","created_at":"2026-07-05T00:15:25.849667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.12977","created_at":"2026-07-05T00:15:25.849667+00:00"},{"alias_kind":"pith_short_12","alias_value":"GKUWYLLAWZN2","created_at":"2026-07-05T00:15:25.849667+00:00"},{"alias_kind":"pith_short_16","alias_value":"GKUWYLLAWZN2BM44","created_at":"2026-07-05T00:15:25.849667+00:00"},{"alias_kind":"pith_short_8","alias_value":"GKUWYLLA","created_at":"2026-07-05T00:15:25.849667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24147","citing_title":"Progressive Alignment Objectives for Aligner-Encoder based ASR","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24147","citing_title":"Progressive Alignment Objectives for Aligner-Encoder based ASR","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2508.12301","citing_title":"WhisperRT -- Turning Whisper into a Causal Streaming Model","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GKUWYLLAWZN2BM44R5QQP33CYT","json":"https://pith.science/pith/GKUWYLLAWZN2BM44R5QQP33CYT.json","graph_json":"https://pith.science/api/pith-number/GKUWYLLAWZN2BM44R5QQP33CYT/graph.json","events_json":"https://pith.science/api/pith-number/GKUWYLLAWZN2BM44R5QQP33CYT/events.json","paper":"https://pith.science/paper/GKUWYLLA"},"agent_actions":{"view_html":"https://pith.science/pith/GKUWYLLAWZN2BM44R5QQP33CYT","download_json":"https://pith.science/pith/GKUWYLLAWZN2BM44R5QQP33CYT.json","view_paper":"https://pith.science/paper/GKUWYLLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.12977&json=true","fetch_graph":"https://pith.science/api/pith-number/GKUWYLLAWZN2BM44R5QQP33CYT/graph.json","fetch_events":"https://pith.science/api/pith-number/GKUWYLLAWZN2BM44R5QQP33CYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GKUWYLLAWZN2BM44R5QQP33CYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GKUWYLLAWZN2BM44R5QQP33CYT/action/storage_attestation","attest_author":"https://pith.science/pith/GKUWYLLAWZN2BM44R5QQP33CYT/action/author_attestation","sign_citation":"https://pith.science/pith/GKUWYLLAWZN2BM44R5QQP33CYT/action/citation_signature","submit_replication":"https://pith.science/pith/GKUWYLLAWZN2BM44R5QQP33CYT/action/replication_record"}},"created_at":"2026-07-05T00:15:25.849667+00:00","updated_at":"2026-07-05T00:15:25.849667+00:00"}