{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OATEABMNPSQV4PWXRM2B5A75MY","short_pith_number":"pith:OATEABMN","schema_version":"1.0","canonical_sha256":"702640058d7ca15e3ed78b341e83fd66343c6da3651a89b393964b237f700910","source":{"kind":"arxiv","id":"2301.02966","version":1},"attestation_state":"computed","paper":{"title":"SpeeChain: A Speech Toolkit for Large-Scale Machine Speech Chain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andros Tjandra, Heli Qi, Sakriani Sakti, Sashi Novitasari, Satoshi Nakamura","submitted_at":"2023-01-08T03:16:56Z","abstract_excerpt":"This paper introduces SpeeChain, an open-source Pytorch-based toolkit designed to develop the machine speech chain for large-scale use. This first release focuses on the TTS-to-ASR chain, a core component of the machine speech chain, that refers to the TTS data augmentation by unspoken text for ASR. To build an efficient pipeline for the large-scale TTS-to-ASR chain, we implement easy-to-use multi-GPU batch-level model inference, multi-dataloader batch generation, and on-the-fly data selection techniques. In this paper, we first explain the overall procedure of the TTS-to-ASR chain and the dif"},"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":"2301.02966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-08T03:16:56Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"9e9fdef597c7f13f99dc76456318d170d7d31cc86d963f94cd64add1fb083641","abstract_canon_sha256":"f1250021b40b60f0d6bf97e17c6eeecbe8cbd4eff542e87ab27ecaf98e5b6d97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:24.072441Z","signature_b64":"UfXbCKc9/up+YwEUJQOMEyh/WC4s4O1D39Cqzrd0WcK7FZfaciYJ/XBvvCyNVs4Gznp2Uj6jTwAPVNIl0uAbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"702640058d7ca15e3ed78b341e83fd66343c6da3651a89b393964b237f700910","last_reissued_at":"2026-07-05T05:31:24.072067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:24.072067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeeChain: A Speech Toolkit for Large-Scale Machine Speech Chain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andros Tjandra, Heli Qi, Sakriani Sakti, Sashi Novitasari, Satoshi Nakamura","submitted_at":"2023-01-08T03:16:56Z","abstract_excerpt":"This paper introduces SpeeChain, an open-source Pytorch-based toolkit designed to develop the machine speech chain for large-scale use. This first release focuses on the TTS-to-ASR chain, a core component of the machine speech chain, that refers to the TTS data augmentation by unspoken text for ASR. To build an efficient pipeline for the large-scale TTS-to-ASR chain, we implement easy-to-use multi-GPU batch-level model inference, multi-dataloader batch generation, and on-the-fly data selection techniques. In this paper, we first explain the overall procedure of the TTS-to-ASR chain and the dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02966","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/2301.02966/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":"2301.02966","created_at":"2026-07-05T05:31:24.072118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.02966v1","created_at":"2026-07-05T05:31:24.072118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02966","created_at":"2026-07-05T05:31:24.072118+00:00"},{"alias_kind":"pith_short_12","alias_value":"OATEABMNPSQV","created_at":"2026-07-05T05:31:24.072118+00:00"},{"alias_kind":"pith_short_16","alias_value":"OATEABMNPSQV4PWX","created_at":"2026-07-05T05:31:24.072118+00:00"},{"alias_kind":"pith_short_8","alias_value":"OATEABMN","created_at":"2026-07-05T05:31:24.072118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18320","citing_title":"Continual Learning in Machine Speech Chain Using Gradient Episodic Memory","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OATEABMNPSQV4PWXRM2B5A75MY","json":"https://pith.science/pith/OATEABMNPSQV4PWXRM2B5A75MY.json","graph_json":"https://pith.science/api/pith-number/OATEABMNPSQV4PWXRM2B5A75MY/graph.json","events_json":"https://pith.science/api/pith-number/OATEABMNPSQV4PWXRM2B5A75MY/events.json","paper":"https://pith.science/paper/OATEABMN"},"agent_actions":{"view_html":"https://pith.science/pith/OATEABMNPSQV4PWXRM2B5A75MY","download_json":"https://pith.science/pith/OATEABMNPSQV4PWXRM2B5A75MY.json","view_paper":"https://pith.science/paper/OATEABMN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.02966&json=true","fetch_graph":"https://pith.science/api/pith-number/OATEABMNPSQV4PWXRM2B5A75MY/graph.json","fetch_events":"https://pith.science/api/pith-number/OATEABMNPSQV4PWXRM2B5A75MY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OATEABMNPSQV4PWXRM2B5A75MY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OATEABMNPSQV4PWXRM2B5A75MY/action/storage_attestation","attest_author":"https://pith.science/pith/OATEABMNPSQV4PWXRM2B5A75MY/action/author_attestation","sign_citation":"https://pith.science/pith/OATEABMNPSQV4PWXRM2B5A75MY/action/citation_signature","submit_replication":"https://pith.science/pith/OATEABMNPSQV4PWXRM2B5A75MY/action/replication_record"}},"created_at":"2026-07-05T05:31:24.072118+00:00","updated_at":"2026-07-05T05:31:24.072118+00:00"}