{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Z366EQE6D4MYX3V7BU26AFDFJO","short_pith_number":"pith:Z366EQE6","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"},"canonical_sha256":"cefde2409e1f198beebf0d35e014654b8b8228cd6a9eaa0e8bf1f2af6d496338","source":{"kind":"arxiv","id":"1803.10299","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Z366EQE6D4MYX3V7BU26AFDFJO","target":"record","payload":{"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"},"canonical_sha256":"cefde2409e1f198beebf0d35e014654b8b8228cd6a9eaa0e8bf1f2af6d496338","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"},"source_kind":"arxiv","source_id":"1803.10299","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7jbAb1i5oFCh3MVTR/JSOF6lPsB6Dd9F6i6tWRgOij4vwwVa7LVMV3ES5vF1piEt5bOWj9QujLLwp2vsoybqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T20:36:09.290982Z"},"content_sha256":"37a29d45ce4747b0040f0d14ec72abbe70942d3b9a1832b8353883cc9ec036e3","schema_version":"1.0","event_id":"sha256:37a29d45ce4747b0040f0d14ec72abbe70942d3b9a1832b8353883cc9ec036e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Z366EQE6D4MYX3V7BU26AFDFJO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1lyR89/+/vCo3OvaEcRx/qGSEZgspc4JWUAkE9yr+Vyry1OUv+olXfBru2Zd62C5D93bwNf1T14vizEofk9ACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T20:36:09.291562Z"},"content_sha256":"877f93164c85f2c2e0b3beee68f07bfb7be8d544881b1101843c87c8fa2908dc","schema_version":"1.0","event_id":"sha256:877f93164c85f2c2e0b3beee68f07bfb7be8d544881b1101843c87c8fa2908dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z366EQE6D4MYX3V7BU26AFDFJO/bundle.json","state_url":"https://pith.science/pith/Z366EQE6D4MYX3V7BU26AFDFJO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z366EQE6D4MYX3V7BU26AFDFJO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-18T20:36:09Z","links":{"resolver":"https://pith.science/pith/Z366EQE6D4MYX3V7BU26AFDFJO","bundle":"https://pith.science/pith/Z366EQE6D4MYX3V7BU26AFDFJO/bundle.json","state":"https://pith.science/pith/Z366EQE6D4MYX3V7BU26AFDFJO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z366EQE6D4MYX3V7BU26AFDFJO/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JRJjnuRcvwv5EUZnry7TRVZS4bhSJMozT3KValZsWSHg3WMC+fJm5dkOnRJIXiyZTC5oB/NpRltlp56yuDhkAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T20:36:09.293468Z","bundle_sha256":"22b3438563cb9d157b74e8322287b7270551855ee5e1517f9ce31ed16ba106c9"}}