{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LLS53GGFXMITIYF4MNDBYZHS7Y","short_pith_number":"pith:LLS53GGF","schema_version":"1.0","canonical_sha256":"5ae5dd98c5bb113460bc63461c64f2fe3fbe0313a494934ef8da4fba86f9da5c","source":{"kind":"arxiv","id":"2011.02099","version":1},"attestation_state":"computed","paper":{"title":"Augmenting Images for ASR and TTS through Single-loop and Dual-loop Multimodal Chain Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andros Tjandra, Johanes Effendi, Sakriani Sakti, Satoshi Nakamura","submitted_at":"2020-11-04T02:26:02Z","abstract_excerpt":"Previous research has proposed a machine speech chain to enable automatic speech recognition (ASR) and text-to-speech synthesis (TTS) to assist each other in semi-supervised learning and to avoid the need for a large amount of paired speech and text data. However, that framework still requires a large amount of unpaired (speech or text) data. A prototype multimodal machine chain was then explored to further reduce the need for a large amount of unpaired data, which could improve ASR or TTS even when no more speech or text data were available. Unfortunately, this framework relied on the image r"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2011.02099","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-04T02:26:02Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"ac4af154bc1b0e5ac6d57613fd62875f66b2ad9c61d3100538b41e952719ace9","abstract_canon_sha256":"60871b354ffc6c20343483a1ed34256b33e4350143ef6f4021d9a746650140c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:09.186846Z","signature_b64":"TDv5CoowpFbYSYsZ/hwjaw4hZtzobpe4NxWpqS0N9uF+/2xkadVZ/aP0fB37LX8ksdYeMASPPgJOrzP3P/BxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ae5dd98c5bb113460bc63461c64f2fe3fbe0313a494934ef8da4fba86f9da5c","last_reissued_at":"2026-07-05T01:49:09.186413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:09.186413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Augmenting Images for ASR and TTS through Single-loop and Dual-loop Multimodal Chain Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andros Tjandra, Johanes Effendi, Sakriani Sakti, Satoshi Nakamura","submitted_at":"2020-11-04T02:26:02Z","abstract_excerpt":"Previous research has proposed a machine speech chain to enable automatic speech recognition (ASR) and text-to-speech synthesis (TTS) to assist each other in semi-supervised learning and to avoid the need for a large amount of paired speech and text data. However, that framework still requires a large amount of unpaired (speech or text) data. A prototype multimodal machine chain was then explored to further reduce the need for a large amount of unpaired data, which could improve ASR or TTS even when no more speech or text data were available. Unfortunately, this framework relied on the image r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02099","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/2011.02099/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2011.02099","created_at":"2026-07-05T01:49:09.186466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.02099v1","created_at":"2026-07-05T01:49:09.186466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02099","created_at":"2026-07-05T01:49:09.186466+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLS53GGFXMIT","created_at":"2026-07-05T01:49:09.186466+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLS53GGFXMITIYF4","created_at":"2026-07-05T01:49:09.186466+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLS53GGF","created_at":"2026-07-05T01:49:09.186466+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LLS53GGFXMITIYF4MNDBYZHS7Y","json":"https://pith.science/pith/LLS53GGFXMITIYF4MNDBYZHS7Y.json","graph_json":"https://pith.science/api/pith-number/LLS53GGFXMITIYF4MNDBYZHS7Y/graph.json","events_json":"https://pith.science/api/pith-number/LLS53GGFXMITIYF4MNDBYZHS7Y/events.json","paper":"https://pith.science/paper/LLS53GGF"},"agent_actions":{"view_html":"https://pith.science/pith/LLS53GGFXMITIYF4MNDBYZHS7Y","download_json":"https://pith.science/pith/LLS53GGFXMITIYF4MNDBYZHS7Y.json","view_paper":"https://pith.science/paper/LLS53GGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.02099&json=true","fetch_graph":"https://pith.science/api/pith-number/LLS53GGFXMITIYF4MNDBYZHS7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/LLS53GGFXMITIYF4MNDBYZHS7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLS53GGFXMITIYF4MNDBYZHS7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLS53GGFXMITIYF4MNDBYZHS7Y/action/storage_attestation","attest_author":"https://pith.science/pith/LLS53GGFXMITIYF4MNDBYZHS7Y/action/author_attestation","sign_citation":"https://pith.science/pith/LLS53GGFXMITIYF4MNDBYZHS7Y/action/citation_signature","submit_replication":"https://pith.science/pith/LLS53GGFXMITIYF4MNDBYZHS7Y/action/replication_record"}},"created_at":"2026-07-05T01:49:09.186466+00:00","updated_at":"2026-07-05T01:49:09.186466+00:00"}