{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QD3CCE3AG2OQRKFF4FE2AGUGFE","short_pith_number":"pith:QD3CCE3A","canonical_record":{"source":{"id":"1811.00707","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T02:15:46Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"14b67761b17842f3565016b4754bfe72efc4cf6d35dea11829e1e625367ae871","abstract_canon_sha256":"a4fe9872807dd69187091ccf5b0962fc74ecd8a75547696aa7bfd9060302a907"},"schema_version":"1.0"},"canonical_sha256":"80f6211360369d08a8a5e149a01a8629240c9fe06001ba27161d185eccdcf1c1","source":{"kind":"arxiv","id":"1811.00707","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00707","created_at":"2026-05-18T00:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00707v1","created_at":"2026-05-18T00:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00707","created_at":"2026-05-18T00:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"QD3CCE3AG2OQ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QD3CCE3AG2OQRKFF","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QD3CCE3A","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QD3CCE3AG2OQRKFF4FE2AGUGFE","target":"record","payload":{"canonical_record":{"source":{"id":"1811.00707","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T02:15:46Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"14b67761b17842f3565016b4754bfe72efc4cf6d35dea11829e1e625367ae871","abstract_canon_sha256":"a4fe9872807dd69187091ccf5b0962fc74ecd8a75547696aa7bfd9060302a907"},"schema_version":"1.0"},"canonical_sha256":"80f6211360369d08a8a5e149a01a8629240c9fe06001ba27161d185eccdcf1c1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:42.432383Z","signature_b64":"MkPtjVvl9qWo5zQ1jKXVkDah1hN1Vd379uRTzpQ7DLICGt7GRSTzDZJT+EQf5DhX8wLwnluTRqGeGHTntyBdDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80f6211360369d08a8a5e149a01a8629240c9fe06001ba27161d185eccdcf1c1","last_reissued_at":"2026-05-18T00:01:42.431825Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:42.431825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.00707","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:01:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1hnuEPC1Qvghk+BEx+PqGiUWmr5jmPPGb0D9Qik7V2i/ubAtpLNkQdf4s3oJDHLq4c0UKFRRwI689shuD3zqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T16:36:51.274644Z"},"content_sha256":"d17a35f92d1755ea9aefe9ca9ed22aea6439cb30e2c36056c6149dc696f72294","schema_version":"1.0","event_id":"sha256:d17a35f92d1755ea9aefe9ca9ed22aea6439cb30e2c36056c6149dc696f72294"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QD3CCE3AG2OQRKFF4FE2AGUGFE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Neural Speech Recognition Systems with Synthetic Speech Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Jason Li, Ravi Gadde, Vitaly Lavrukhin","submitted_at":"2018-11-02T02:15:46Z","abstract_excerpt":"Building an accurate automatic speech recognition (ASR) system requires a large dataset that contains many hours of labeled speech samples produced by a diverse set of speakers. The lack of such open free datasets is one of the main issues preventing advancements in ASR research. To address this problem, we propose to augment a natural speech dataset with synthetic speech. We train very large end-to-end neural speech recognition models using the LibriSpeech dataset augmented with synthetic speech. These new models achieve state of the art Word Error Rate (WER) for character-level based models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00707","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":""},"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":"2026-05-18T00:01:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RcUbTl9hFuzKbY+RVubM0GN2I+b74O+Ldo5PpKmaoZos4nwdRrsyGqTFdRHOPm57IQVCys0aT9nPXx02c3ydAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T16:36:51.275305Z"},"content_sha256":"3b19ef7c8b1a5b5a31d4c10e420accda25fe6198ff133db098a9e42b9da9f8d5","schema_version":"1.0","event_id":"sha256:3b19ef7c8b1a5b5a31d4c10e420accda25fe6198ff133db098a9e42b9da9f8d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE/bundle.json","state_url":"https://pith.science/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE/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":"2026-05-26T16:36:51Z","links":{"resolver":"https://pith.science/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE","bundle":"https://pith.science/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE/bundle.json","state":"https://pith.science/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QD3CCE3AG2OQRKFF4FE2AGUGFE","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":"a4fe9872807dd69187091ccf5b0962fc74ecd8a75547696aa7bfd9060302a907","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T02:15:46Z","title_canon_sha256":"14b67761b17842f3565016b4754bfe72efc4cf6d35dea11829e1e625367ae871"},"schema_version":"1.0","source":{"id":"1811.00707","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00707","created_at":"2026-05-18T00:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00707v1","created_at":"2026-05-18T00:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00707","created_at":"2026-05-18T00:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"QD3CCE3AG2OQ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QD3CCE3AG2OQRKFF","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QD3CCE3A","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:3b19ef7c8b1a5b5a31d4c10e420accda25fe6198ff133db098a9e42b9da9f8d5","target":"graph","created_at":"2026-05-18T00:01:42Z","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":"Building an accurate automatic speech recognition (ASR) system requires a large dataset that contains many hours of labeled speech samples produced by a diverse set of speakers. The lack of such open free datasets is one of the main issues preventing advancements in ASR research. To address this problem, we propose to augment a natural speech dataset with synthetic speech. We train very large end-to-end neural speech recognition models using the LibriSpeech dataset augmented with synthetic speech. These new models achieve state of the art Word Error Rate (WER) for character-level based models ","authors_text":"Boris Ginsburg, Jason Li, Ravi Gadde, Vitaly Lavrukhin","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T02:15:46Z","title":"Training Neural Speech Recognition Systems with Synthetic Speech Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00707","kind":"arxiv","version":1},"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:d17a35f92d1755ea9aefe9ca9ed22aea6439cb30e2c36056c6149dc696f72294","target":"record","created_at":"2026-05-18T00:01:42Z","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":"a4fe9872807dd69187091ccf5b0962fc74ecd8a75547696aa7bfd9060302a907","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T02:15:46Z","title_canon_sha256":"14b67761b17842f3565016b4754bfe72efc4cf6d35dea11829e1e625367ae871"},"schema_version":"1.0","source":{"id":"1811.00707","kind":"arxiv","version":1}},"canonical_sha256":"80f6211360369d08a8a5e149a01a8629240c9fe06001ba27161d185eccdcf1c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80f6211360369d08a8a5e149a01a8629240c9fe06001ba27161d185eccdcf1c1","first_computed_at":"2026-05-18T00:01:42.431825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:42.431825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MkPtjVvl9qWo5zQ1jKXVkDah1hN1Vd379uRTzpQ7DLICGt7GRSTzDZJT+EQf5DhX8wLwnluTRqGeGHTntyBdDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:42.432383Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.00707","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d17a35f92d1755ea9aefe9ca9ed22aea6439cb30e2c36056c6149dc696f72294","sha256:3b19ef7c8b1a5b5a31d4c10e420accda25fe6198ff133db098a9e42b9da9f8d5"],"state_sha256":"ebab802ba9735d0c56c71ca889b2cc412c9f5b5afd3eca68b1c128ed8808a43a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fSQG6wiNFmnbSCRJv5Cqb6aM+tNbwkYtJf7GY5cuEun9+uoVR78/Kt1dJba5St8nzjMcipW5x/rIpF28d2AkCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T16:36:51.278948Z","bundle_sha256":"584004ca84d91c5435f8fb4863371a37962b20f1eba7d787f54fbaf00676291a"}}