{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Z366EQE6D4MYX3V7BU26AFDFJO","short_pith_number":"pith:Z366EQE6","schema_version":"1.0","canonical_sha256":"cefde2409e1f198beebf0d35e014654b8b8228cd6a9eaa0e8bf1f2af6d496338","source":{"kind":"arxiv","id":"1803.10299","version":3},"attestation_state":"computed","paper":{"title":"Multi-Modal Data Augmentation for End-to-End ASR","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Adithya Renduchintala, Matthew Wiesner, Shinji Watanabe, Shuoyang Ding","submitted_at":"2018-03-27T20:12:39Z","abstract_excerpt":"We present a new end-to-end architecture for automatic speech recognition (ASR) that can be trained using \\emph{symbolic} input in addition to the traditional acoustic input. This architecture utilizes two separate encoders: one for acoustic input and another for symbolic input, both sharing the attention and decoder parameters. We call this architecture a multi-modal data augmentation network (MMDA), as it can support multi-modal (acoustic and symbolic) input and enables seamless mixing of large text datasets with significantly smaller transcribed speech corpora during training. We study diff"},"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":"1803.10299","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-27T20:12:39Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"f142565998c2df464d3b61bb1af47636f88fc22f4feb74925162ff89eaecba73","abstract_canon_sha256":"72d257fe84da106305579c2aad9a1450be21959403e1c1e013839d89d36a91b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:04.321896Z","signature_b64":"IW4leI5clXZ2e6DRCdRIkKGzTEJty/TA2ymPbe3fr+JN3TqYjFfkLUktWqn77AjcGxK1qITFLeOQW4a4tuTrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cefde2409e1f198beebf0d35e014654b8b8228cd6a9eaa0e8bf1f2af6d496338","last_reissued_at":"2026-05-18T00:13:04.321185Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:04.321185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Modal Data Augmentation for End-to-End ASR","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Adithya Renduchintala, Matthew Wiesner, Shinji Watanabe, Shuoyang Ding","submitted_at":"2018-03-27T20:12:39Z","abstract_excerpt":"We present a new end-to-end architecture for automatic speech recognition (ASR) that can be trained using \\emph{symbolic} input in addition to the traditional acoustic input. This architecture utilizes two separate encoders: one for acoustic input and another for symbolic input, both sharing the attention and decoder parameters. We call this architecture a multi-modal data augmentation network (MMDA), as it can support multi-modal (acoustic and symbolic) input and enables seamless mixing of large text datasets with significantly smaller transcribed speech corpora during training. We study diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10299","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1803.10299","created_at":"2026-05-18T00:13:04.321290+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.10299v3","created_at":"2026-05-18T00:13:04.321290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10299","created_at":"2026-05-18T00:13:04.321290+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z366EQE6D4MY","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z366EQE6D4MYX3V7","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z366EQE6","created_at":"2026-05-18T12:33:04.347982+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/Z366EQE6D4MYX3V7BU26AFDFJO","json":"https://pith.science/pith/Z366EQE6D4MYX3V7BU26AFDFJO.json","graph_json":"https://pith.science/api/pith-number/Z366EQE6D4MYX3V7BU26AFDFJO/graph.json","events_json":"https://pith.science/api/pith-number/Z366EQE6D4MYX3V7BU26AFDFJO/events.json","paper":"https://pith.science/paper/Z366EQE6"},"agent_actions":{"view_html":"https://pith.science/pith/Z366EQE6D4MYX3V7BU26AFDFJO","download_json":"https://pith.science/pith/Z366EQE6D4MYX3V7BU26AFDFJO.json","view_paper":"https://pith.science/paper/Z366EQE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.10299&json=true","fetch_graph":"https://pith.science/api/pith-number/Z366EQE6D4MYX3V7BU26AFDFJO/graph.json","fetch_events":"https://pith.science/api/pith-number/Z366EQE6D4MYX3V7BU26AFDFJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z366EQE6D4MYX3V7BU26AFDFJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z366EQE6D4MYX3V7BU26AFDFJO/action/storage_attestation","attest_author":"https://pith.science/pith/Z366EQE6D4MYX3V7BU26AFDFJO/action/author_attestation","sign_citation":"https://pith.science/pith/Z366EQE6D4MYX3V7BU26AFDFJO/action/citation_signature","submit_replication":"https://pith.science/pith/Z366EQE6D4MYX3V7BU26AFDFJO/action/replication_record"}},"created_at":"2026-05-18T00:13:04.321290+00:00","updated_at":"2026-05-18T00:13:04.321290+00:00"}