{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FEPZYMEF5RZAIGBNLVRSWMBRCK","short_pith_number":"pith:FEPZYMEF","schema_version":"1.0","canonical_sha256":"291f9c3085ec7204182d5d632b303112af4360d77aef52a4aa0b30e3c417bfd6","source":{"kind":"arxiv","id":"2205.12007","version":1},"attestation_state":"computed","paper":{"title":"PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dianhai Yu, Enlei Gong, Hui Zhang, Junkun Chen, Liang Huang, Renjie Zheng, Tian Yuan, Xiaoguang Hu, Xiaojie Chen, Xintong Li, Yanjun Ma, Yuxin Huang, Zeyu Chen","submitted_at":"2022-05-20T10:14:53Z","abstract_excerpt":"PaddleSpeech is an open-source all-in-one speech toolkit. It aims at facilitating the development and research of speech processing technologies by providing an easy-to-use command-line interface and a simple code structure. This paper describes the design philosophy and core architecture of PaddleSpeech to support several essential speech-to-text and text-to-speech tasks. PaddleSpeech achieves competitive or state-of-the-art performance on various speech datasets and implements the most popular methods. It also provides recipes and pretrained models to quickly reproduce the experimental resul"},"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":"2205.12007","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-05-20T10:14:53Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"696d57ae37fba4210345cb029d85f38c7436eb67f34b7c520525bf3831ddd87d","abstract_canon_sha256":"695b8369888f0298d2a4af19e055f0dbcf2d4b8b3cbd507780f8b24085931f75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:10.507694Z","signature_b64":"hHzXsB4Jg06xVwq8mzy0G37z57udJGfN8yaOA+6CkpU1tjPwGuXs0+avIbRm1AuNNUvjQ8Wg241EtxgfdsCiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"291f9c3085ec7204182d5d632b303112af4360d77aef52a4aa0b30e3c417bfd6","last_reissued_at":"2026-07-05T04:26:10.507357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:10.507357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dianhai Yu, Enlei Gong, Hui Zhang, Junkun Chen, Liang Huang, Renjie Zheng, Tian Yuan, Xiaoguang Hu, Xiaojie Chen, Xintong Li, Yanjun Ma, Yuxin Huang, Zeyu Chen","submitted_at":"2022-05-20T10:14:53Z","abstract_excerpt":"PaddleSpeech is an open-source all-in-one speech toolkit. It aims at facilitating the development and research of speech processing technologies by providing an easy-to-use command-line interface and a simple code structure. This paper describes the design philosophy and core architecture of PaddleSpeech to support several essential speech-to-text and text-to-speech tasks. PaddleSpeech achieves competitive or state-of-the-art performance on various speech datasets and implements the most popular methods. It also provides recipes and pretrained models to quickly reproduce the experimental resul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12007","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/2205.12007/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":"2205.12007","created_at":"2026-07-05T04:26:10.507410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12007v1","created_at":"2026-07-05T04:26:10.507410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12007","created_at":"2026-07-05T04:26:10.507410+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEPZYMEF5RZA","created_at":"2026-07-05T04:26:10.507410+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEPZYMEF5RZAIGBN","created_at":"2026-07-05T04:26:10.507410+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEPZYMEF","created_at":"2026-07-05T04:26:10.507410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16969","citing_title":"State-Space Models in Efficient Whispered and Multi-dialect Speech Recognition","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEPZYMEF5RZAIGBNLVRSWMBRCK","json":"https://pith.science/pith/FEPZYMEF5RZAIGBNLVRSWMBRCK.json","graph_json":"https://pith.science/api/pith-number/FEPZYMEF5RZAIGBNLVRSWMBRCK/graph.json","events_json":"https://pith.science/api/pith-number/FEPZYMEF5RZAIGBNLVRSWMBRCK/events.json","paper":"https://pith.science/paper/FEPZYMEF"},"agent_actions":{"view_html":"https://pith.science/pith/FEPZYMEF5RZAIGBNLVRSWMBRCK","download_json":"https://pith.science/pith/FEPZYMEF5RZAIGBNLVRSWMBRCK.json","view_paper":"https://pith.science/paper/FEPZYMEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12007&json=true","fetch_graph":"https://pith.science/api/pith-number/FEPZYMEF5RZAIGBNLVRSWMBRCK/graph.json","fetch_events":"https://pith.science/api/pith-number/FEPZYMEF5RZAIGBNLVRSWMBRCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEPZYMEF5RZAIGBNLVRSWMBRCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEPZYMEF5RZAIGBNLVRSWMBRCK/action/storage_attestation","attest_author":"https://pith.science/pith/FEPZYMEF5RZAIGBNLVRSWMBRCK/action/author_attestation","sign_citation":"https://pith.science/pith/FEPZYMEF5RZAIGBNLVRSWMBRCK/action/citation_signature","submit_replication":"https://pith.science/pith/FEPZYMEF5RZAIGBNLVRSWMBRCK/action/replication_record"}},"created_at":"2026-07-05T04:26:10.507410+00:00","updated_at":"2026-07-05T04:26:10.507410+00:00"}