{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:W4QFWMDTPBE7WCDUXU67RAXLKN","short_pith_number":"pith:W4QFWMDT","canonical_record":{"source":{"id":"2106.07803","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-14T23:26:44Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"9f4c3569e38e9ce4a804bad9dc25b7530ce1af9f9f1a41e51a6c37c8825eeb63","abstract_canon_sha256":"80b7277ecd190bb36eaa62002c519c2626fd424861a13b178639d1b9025cd916"},"schema_version":"1.0"},"canonical_sha256":"b7205b30737849fb0874bd3df882eb536079ff0106415bb3dd911cc4dbbc8c10","source":{"kind":"arxiv","id":"2106.07803","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.07803","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"2106.07803v1","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07803","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"W4QFWMDTPBE7","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"pith_short_16","alias_value":"W4QFWMDTPBE7WCDU","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"pith_short_8","alias_value":"W4QFWMDT","created_at":"2026-07-05T02:49:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:W4QFWMDTPBE7WCDUXU67RAXLKN","target":"record","payload":{"canonical_record":{"source":{"id":"2106.07803","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-14T23:26:44Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"9f4c3569e38e9ce4a804bad9dc25b7530ce1af9f9f1a41e51a6c37c8825eeb63","abstract_canon_sha256":"80b7277ecd190bb36eaa62002c519c2626fd424861a13b178639d1b9025cd916"},"schema_version":"1.0"},"canonical_sha256":"b7205b30737849fb0874bd3df882eb536079ff0106415bb3dd911cc4dbbc8c10","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:33.944486Z","signature_b64":"g+9zGIcM1LNBWin1lOO7wBnemhQwQVBZ1IVofWDAHrZ3wCXyXdxWOZ04eBWReQPqjzLUgFPewMsPCUf5fEywBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7205b30737849fb0874bd3df882eb536079ff0106415bb3dd911cc4dbbc8c10","last_reissued_at":"2026-07-05T02:49:33.944017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:33.944017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.07803","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":"2026-07-05T02:49:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RYaG15sfhTh8QibFzp2wvPqqccvm5L7RpGEuk1SaeVGwW4304ipaLwRu8V6zG5DA7ZiZgVnec2m0G+XpIAOOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:29:50.789467Z"},"content_sha256":"f998dc32b90646caec6d6d1fae0b69553e3e6be5cc58eedf7de6ddfa5a9ac74d","schema_version":"1.0","event_id":"sha256:f998dc32b90646caec6d6d1fae0b69553e3e6be5cc58eedf7de6ddfa5a9ac74d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:W4QFWMDTPBE7WCDUXU67RAXLKN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SynthASR: Unlocking Synthetic Data for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Amin Fazel, Jasha Droppo, Roberto Barra-Chicote, Roland Maas, Wei Yang, Yixiong Meng, Yulan Liu","submitted_at":"2021-06-14T23:26:44Z","abstract_excerpt":"End-to-end (E2E) automatic speech recognition (ASR) models have recently demonstrated superior performance over the traditional hybrid ASR models. Training an E2E ASR model requires a large amount of data which is not only expensive but may also raise dependency on production data. At the same time, synthetic speech generated by the state-of-the-art text-to-speech (TTS) engines has advanced to near-human naturalness. In this work, we propose to utilize synthetic speech for ASR training (SynthASR) in applications where data is sparse or hard to get for ASR model training. In addition, we apply "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07803","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/2106.07803/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:49:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EyJEM6AT1mTvP3nIUjaWS3y9XwIXnL1B9AXqkN6GuEGfTsjpVJjk5oIdKa21UnugTrC9pQ5zmfDKiOyI7+3MCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:29:50.790132Z"},"content_sha256":"b8f4ce5324ad927d2d14a44ace79ff96d7ed124632d601b861a4910846c5446e","schema_version":"1.0","event_id":"sha256:b8f4ce5324ad927d2d14a44ace79ff96d7ed124632d601b861a4910846c5446e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W4QFWMDTPBE7WCDUXU67RAXLKN/bundle.json","state_url":"https://pith.science/pith/W4QFWMDTPBE7WCDUXU67RAXLKN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W4QFWMDTPBE7WCDUXU67RAXLKN/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":"2026-07-07T05:29:50Z","links":{"resolver":"https://pith.science/pith/W4QFWMDTPBE7WCDUXU67RAXLKN","bundle":"https://pith.science/pith/W4QFWMDTPBE7WCDUXU67RAXLKN/bundle.json","state":"https://pith.science/pith/W4QFWMDTPBE7WCDUXU67RAXLKN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W4QFWMDTPBE7WCDUXU67RAXLKN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:W4QFWMDTPBE7WCDUXU67RAXLKN","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":"80b7277ecd190bb36eaa62002c519c2626fd424861a13b178639d1b9025cd916","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-14T23:26:44Z","title_canon_sha256":"9f4c3569e38e9ce4a804bad9dc25b7530ce1af9f9f1a41e51a6c37c8825eeb63"},"schema_version":"1.0","source":{"id":"2106.07803","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.07803","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"2106.07803v1","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07803","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"W4QFWMDTPBE7","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"pith_short_16","alias_value":"W4QFWMDTPBE7WCDU","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"pith_short_8","alias_value":"W4QFWMDT","created_at":"2026-07-05T02:49:33Z"}],"graph_snapshots":[{"event_id":"sha256:b8f4ce5324ad927d2d14a44ace79ff96d7ed124632d601b861a4910846c5446e","target":"graph","created_at":"2026-07-05T02:49:33Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.07803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end (E2E) automatic speech recognition (ASR) models have recently demonstrated superior performance over the traditional hybrid ASR models. Training an E2E ASR model requires a large amount of data which is not only expensive but may also raise dependency on production data. At the same time, synthetic speech generated by the state-of-the-art text-to-speech (TTS) engines has advanced to near-human naturalness. In this work, we propose to utilize synthetic speech for ASR training (SynthASR) in applications where data is sparse or hard to get for ASR model training. In addition, we apply ","authors_text":"Amin Fazel, Jasha Droppo, Roberto Barra-Chicote, Roland Maas, Wei Yang, Yixiong Meng, Yulan Liu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-14T23:26:44Z","title":"SynthASR: Unlocking Synthetic Data for Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07803","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:f998dc32b90646caec6d6d1fae0b69553e3e6be5cc58eedf7de6ddfa5a9ac74d","target":"record","created_at":"2026-07-05T02:49:33Z","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":"80b7277ecd190bb36eaa62002c519c2626fd424861a13b178639d1b9025cd916","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-14T23:26:44Z","title_canon_sha256":"9f4c3569e38e9ce4a804bad9dc25b7530ce1af9f9f1a41e51a6c37c8825eeb63"},"schema_version":"1.0","source":{"id":"2106.07803","kind":"arxiv","version":1}},"canonical_sha256":"b7205b30737849fb0874bd3df882eb536079ff0106415bb3dd911cc4dbbc8c10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7205b30737849fb0874bd3df882eb536079ff0106415bb3dd911cc4dbbc8c10","first_computed_at":"2026-07-05T02:49:33.944017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:33.944017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g+9zGIcM1LNBWin1lOO7wBnemhQwQVBZ1IVofWDAHrZ3wCXyXdxWOZ04eBWReQPqjzLUgFPewMsPCUf5fEywBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:33.944486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.07803","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f998dc32b90646caec6d6d1fae0b69553e3e6be5cc58eedf7de6ddfa5a9ac74d","sha256:b8f4ce5324ad927d2d14a44ace79ff96d7ed124632d601b861a4910846c5446e"],"state_sha256":"253dd8b53c4b5d9c9ed77c93a3f559b336eb3e92c041eebd8af08f282b6e1c30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"slvtyUQj9RDJcBPuhUXwUATvWS5Slu2bMTfObkMfRHcUAwBPPRH02KxQi827semO1OXbfCdNRqwKzwJq6wYiDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:29:50.793152Z","bundle_sha256":"ffe32c2b51eecb0c6533eeb5371caf8be1d6f3f9132847b61835c71872a21517"}}