{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Z366EQE6D4MYX3V7BU26AFDFJO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"72d257fe84da106305579c2aad9a1450be21959403e1c1e013839d89d36a91b5","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-27T20:12:39Z","title_canon_sha256":"f142565998c2df464d3b61bb1af47636f88fc22f4feb74925162ff89eaecba73"},"schema_version":"1.0","source":{"id":"1803.10299","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.10299","created_at":"2026-05-18T00:13:04Z"},{"alias_kind":"arxiv_version","alias_value":"1803.10299v3","created_at":"2026-05-18T00:13:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10299","created_at":"2026-05-18T00:13:04Z"},{"alias_kind":"pith_short_12","alias_value":"Z366EQE6D4MY","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Z366EQE6D4MYX3V7","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Z366EQE6","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:877f93164c85f2c2e0b3beee68f07bfb7be8d544881b1101843c87c8fa2908dc","target":"graph","created_at":"2026-05-18T00:13:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Adithya Renduchintala, Matthew Wiesner, Shinji Watanabe, Shuoyang Ding","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-27T20:12:39Z","title":"Multi-Modal Data Augmentation for End-to-End ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10299","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:37a29d45ce4747b0040f0d14ec72abbe70942d3b9a1832b8353883cc9ec036e3","target":"record","created_at":"2026-05-18T00:13:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"72d257fe84da106305579c2aad9a1450be21959403e1c1e013839d89d36a91b5","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-27T20:12:39Z","title_canon_sha256":"f142565998c2df464d3b61bb1af47636f88fc22f4feb74925162ff89eaecba73"},"schema_version":"1.0","source":{"id":"1803.10299","kind":"arxiv","version":3}},"canonical_sha256":"cefde2409e1f198beebf0d35e014654b8b8228cd6a9eaa0e8bf1f2af6d496338","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cefde2409e1f198beebf0d35e014654b8b8228cd6a9eaa0e8bf1f2af6d496338","first_computed_at":"2026-05-18T00:13:04.321185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:04.321185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IW4leI5clXZ2e6DRCdRIkKGzTEJty/TA2ymPbe3fr+JN3TqYjFfkLUktWqn77AjcGxK1qITFLeOQW4a4tuTrCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:04.321896Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.10299","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37a29d45ce4747b0040f0d14ec72abbe70942d3b9a1832b8353883cc9ec036e3","sha256:877f93164c85f2c2e0b3beee68f07bfb7be8d544881b1101843c87c8fa2908dc"],"state_sha256":"5099d89f660c1520185c6dd33f055dcd2c6384b74ad98a344d12ce81f06fb96b"}