{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JUTVWQOGFER4Q7IROFGSBSTS4Q","short_pith_number":"pith:JUTVWQOG","canonical_record":{"source":{"id":"2508.21631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-29T13:46:41Z","cross_cats_sorted":[],"title_canon_sha256":"0077055508409458057ab798aa1209267ea43b551a1e77a85e2a5d658951881c","abstract_canon_sha256":"09e761b7a7721fd7687c13bc0cdaa2cb6a4961a065932c17bca3b0523002881e"},"schema_version":"1.0"},"canonical_sha256":"4d275b41c62923c87d11714d20ca72e411c1d1e9c70c46fc14fa4c1a3bb373cd","source":{"kind":"arxiv","id":"2508.21631","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21631","created_at":"2026-07-05T12:01:46Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21631v1","created_at":"2026-07-05T12:01:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21631","created_at":"2026-07-05T12:01:46Z"},{"alias_kind":"pith_short_12","alias_value":"JUTVWQOGFER4","created_at":"2026-07-05T12:01:46Z"},{"alias_kind":"pith_short_16","alias_value":"JUTVWQOGFER4Q7IR","created_at":"2026-07-05T12:01:46Z"},{"alias_kind":"pith_short_8","alias_value":"JUTVWQOG","created_at":"2026-07-05T12:01:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JUTVWQOGFER4Q7IROFGSBSTS4Q","target":"record","payload":{"canonical_record":{"source":{"id":"2508.21631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-29T13:46:41Z","cross_cats_sorted":[],"title_canon_sha256":"0077055508409458057ab798aa1209267ea43b551a1e77a85e2a5d658951881c","abstract_canon_sha256":"09e761b7a7721fd7687c13bc0cdaa2cb6a4961a065932c17bca3b0523002881e"},"schema_version":"1.0"},"canonical_sha256":"4d275b41c62923c87d11714d20ca72e411c1d1e9c70c46fc14fa4c1a3bb373cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:46.901037Z","signature_b64":"S9VirC4Cm2eX5ezGvPl138u2G745Tyct99Q4pF13HkShck9z+CJAGdLO/8/b3o5A4M4Ar9O9lnDrNz50zqGqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d275b41c62923c87d11714d20ca72e411c1d1e9c70c46fc14fa4c1a3bb373cd","last_reissued_at":"2026-07-05T12:01:46.900540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:46.900540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.21631","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":"2026-07-05T12:01:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8NFwy56d0w1kzgdlC94jl8CyymffcKgo8hzmjxRAyX2Sw7Q0IPhiRDPAJYK28b1ArSh0ZwEmn60nEiQ0OHVfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T11:12:38.878789Z"},"content_sha256":"1ab04ad27524475098a6673188d762ad44dc3cd3d9e853e2f2f9a02be0997711","schema_version":"1.0","event_id":"sha256:1ab04ad27524475098a6673188d762ad44dc3cd3d9e853e2f2f9a02be0997711"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JUTVWQOGFER4Q7IROFGSBSTS4Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Improved Speech Recognition through Optimized Synthetic Data Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Gilles Boulianne, Yanis Perrin","submitted_at":"2025-08-29T13:46:41Z","abstract_excerpt":"Supervised training of speech recognition models requires access to transcribed audio data, which often is not possible due to confidentiality issues. Our approach to this problem is to generate synthetic audio from a text-only corpus using a state-of-the-art text-to-speech model with voice cloning capabilities. Our goal is to achieve automatic speech recognition (ASR) performance comparable to models trained on real data. We explore ways to optimize synthetic data generation through finetuning, filtering and evaluation, and its use for training an end-to-end encoder-decoder ASR model. Experim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21631","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/2508.21631/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":"2026-07-05T12:01:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mOIEOAuiBJ2Z4ey7hGy+wqL+sj1gKiz+uT29fGlyf4fbxnAOEmoZpKz639u+WWoTlnIqf7BFPuYRzaFnnkWoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T11:12:38.879152Z"},"content_sha256":"34e23f28eaff0920a351677d7481cb80ac1c0aeee7b2e7f2385213ea7bb9dcc4","schema_version":"1.0","event_id":"sha256:34e23f28eaff0920a351677d7481cb80ac1c0aeee7b2e7f2385213ea7bb9dcc4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JUTVWQOGFER4Q7IROFGSBSTS4Q/bundle.json","state_url":"https://pith.science/pith/JUTVWQOGFER4Q7IROFGSBSTS4Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JUTVWQOGFER4Q7IROFGSBSTS4Q/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":"2026-07-23T11:12:38Z","links":{"resolver":"https://pith.science/pith/JUTVWQOGFER4Q7IROFGSBSTS4Q","bundle":"https://pith.science/pith/JUTVWQOGFER4Q7IROFGSBSTS4Q/bundle.json","state":"https://pith.science/pith/JUTVWQOGFER4Q7IROFGSBSTS4Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JUTVWQOGFER4Q7IROFGSBSTS4Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JUTVWQOGFER4Q7IROFGSBSTS4Q","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":"09e761b7a7721fd7687c13bc0cdaa2cb6a4961a065932c17bca3b0523002881e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-29T13:46:41Z","title_canon_sha256":"0077055508409458057ab798aa1209267ea43b551a1e77a85e2a5d658951881c"},"schema_version":"1.0","source":{"id":"2508.21631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21631","created_at":"2026-07-05T12:01:46Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21631v1","created_at":"2026-07-05T12:01:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21631","created_at":"2026-07-05T12:01:46Z"},{"alias_kind":"pith_short_12","alias_value":"JUTVWQOGFER4","created_at":"2026-07-05T12:01:46Z"},{"alias_kind":"pith_short_16","alias_value":"JUTVWQOGFER4Q7IR","created_at":"2026-07-05T12:01:46Z"},{"alias_kind":"pith_short_8","alias_value":"JUTVWQOG","created_at":"2026-07-05T12:01:46Z"}],"graph_snapshots":[{"event_id":"sha256:34e23f28eaff0920a351677d7481cb80ac1c0aeee7b2e7f2385213ea7bb9dcc4","target":"graph","created_at":"2026-07-05T12:01:46Z","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/2508.21631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised training of speech recognition models requires access to transcribed audio data, which often is not possible due to confidentiality issues. Our approach to this problem is to generate synthetic audio from a text-only corpus using a state-of-the-art text-to-speech model with voice cloning capabilities. Our goal is to achieve automatic speech recognition (ASR) performance comparable to models trained on real data. We explore ways to optimize synthetic data generation through finetuning, filtering and evaluation, and its use for training an end-to-end encoder-decoder ASR model. Experim","authors_text":"Gilles Boulianne, Yanis Perrin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-29T13:46:41Z","title":"Towards Improved Speech Recognition through Optimized Synthetic Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21631","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":"sha256:1ab04ad27524475098a6673188d762ad44dc3cd3d9e853e2f2f9a02be0997711","target":"record","created_at":"2026-07-05T12:01:46Z","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":"09e761b7a7721fd7687c13bc0cdaa2cb6a4961a065932c17bca3b0523002881e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-29T13:46:41Z","title_canon_sha256":"0077055508409458057ab798aa1209267ea43b551a1e77a85e2a5d658951881c"},"schema_version":"1.0","source":{"id":"2508.21631","kind":"arxiv","version":1}},"canonical_sha256":"4d275b41c62923c87d11714d20ca72e411c1d1e9c70c46fc14fa4c1a3bb373cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d275b41c62923c87d11714d20ca72e411c1d1e9c70c46fc14fa4c1a3bb373cd","first_computed_at":"2026-07-05T12:01:46.900540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:46.900540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S9VirC4Cm2eX5ezGvPl138u2G745Tyct99Q4pF13HkShck9z+CJAGdLO/8/b3o5A4M4Ar9O9lnDrNz50zqGqBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:46.901037Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ab04ad27524475098a6673188d762ad44dc3cd3d9e853e2f2f9a02be0997711","sha256:34e23f28eaff0920a351677d7481cb80ac1c0aeee7b2e7f2385213ea7bb9dcc4"],"state_sha256":"6d0b1c2cba9e7cb0267204bf86a803633a94a04f8dafcd49cabfc7ef51d3d9e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iR7KWgt3xmwxi47PPf/6UU0rerz+2MjcMNOzwdllP+sD04qbqE/mcKzLZyifhIULMfDmU1yy8H9U1sMkDTXEAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-23T11:12:38.881627Z","bundle_sha256":"52a3f415afaa94b7e26553caa6b525b74e57c3feaba2c36ebfa92841a9b074b4"}}