{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XYR5XDGYMGAM5DZHRGOIZEIWY5","short_pith_number":"pith:XYR5XDGY","schema_version":"1.0","canonical_sha256":"be23db8cd86180ce8f27899c8c9116c7533094f4f7579672de136942d5997b2f","source":{"kind":"arxiv","id":"2105.03070","version":2},"attestation_state":"computed","paper":{"title":"SpeechNet: A Universal Modularized Model for Speech Processing Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Cheng-Kuang Lee, Chi-Liang Liu, Da-Rong Liu, Hung-yi Lee, Jheng-Hao Lin, Kai-Wei Chang, Po-Han Chi, Shu-wen Yang, Sung-Feng Huang, Yi-Chen Chen","submitted_at":"2021-05-07T05:31:34Z","abstract_excerpt":"There is a wide variety of speech processing tasks ranging from extracting content information from speech signals to generating speech signals. For different tasks, model networks are usually designed and tuned separately. If a universal model can perform multiple speech processing tasks, some tasks might be improved with the related abilities learned from other tasks. The multi-task learning of a wide variety of speech processing tasks with a universal model has not been studied. This paper proposes a universal modularized model, SpeechNet, which treats all speech processing tasks into a spe"},"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":"2105.03070","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-07T05:31:34Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"915d56f22ad07d6514df2b0a4381e8312a37a0ea83592437f03f6e48b173db7a","abstract_canon_sha256":"4b5de88eae4f4901c4e77528bc3f968de3c752cd9606c0d6717c1dc116752a8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:37.281985Z","signature_b64":"ZL/gJmSsBv7GKiSN1lqt+Zr1hU0Uqvf2rqcRjRmqdNhVrtB7Zr1YxFDpLRI//lVVfIl9hFVUbpVwmUf8pX7MAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be23db8cd86180ce8f27899c8c9116c7533094f4f7579672de136942d5997b2f","last_reissued_at":"2026-07-05T02:44:37.281491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:37.281491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeechNet: A Universal Modularized Model for Speech Processing Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Cheng-Kuang Lee, Chi-Liang Liu, Da-Rong Liu, Hung-yi Lee, Jheng-Hao Lin, Kai-Wei Chang, Po-Han Chi, Shu-wen Yang, Sung-Feng Huang, Yi-Chen Chen","submitted_at":"2021-05-07T05:31:34Z","abstract_excerpt":"There is a wide variety of speech processing tasks ranging from extracting content information from speech signals to generating speech signals. For different tasks, model networks are usually designed and tuned separately. If a universal model can perform multiple speech processing tasks, some tasks might be improved with the related abilities learned from other tasks. The multi-task learning of a wide variety of speech processing tasks with a universal model has not been studied. This paper proposes a universal modularized model, SpeechNet, which treats all speech processing tasks into a spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03070","kind":"arxiv","version":2},"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/2105.03070/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":"2105.03070","created_at":"2026-07-05T02:44:37.281550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.03070v2","created_at":"2026-07-05T02:44:37.281550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03070","created_at":"2026-07-05T02:44:37.281550+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYR5XDGYMGAM","created_at":"2026-07-05T02:44:37.281550+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYR5XDGYMGAM5DZH","created_at":"2026-07-05T02:44:37.281550+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYR5XDGY","created_at":"2026-07-05T02:44:37.281550+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.02612","citing_title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2311.07919","citing_title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2407.10759","citing_title":"Qwen2-Audio Technical Report","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYR5XDGYMGAM5DZHRGOIZEIWY5","json":"https://pith.science/pith/XYR5XDGYMGAM5DZHRGOIZEIWY5.json","graph_json":"https://pith.science/api/pith-number/XYR5XDGYMGAM5DZHRGOIZEIWY5/graph.json","events_json":"https://pith.science/api/pith-number/XYR5XDGYMGAM5DZHRGOIZEIWY5/events.json","paper":"https://pith.science/paper/XYR5XDGY"},"agent_actions":{"view_html":"https://pith.science/pith/XYR5XDGYMGAM5DZHRGOIZEIWY5","download_json":"https://pith.science/pith/XYR5XDGYMGAM5DZHRGOIZEIWY5.json","view_paper":"https://pith.science/paper/XYR5XDGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.03070&json=true","fetch_graph":"https://pith.science/api/pith-number/XYR5XDGYMGAM5DZHRGOIZEIWY5/graph.json","fetch_events":"https://pith.science/api/pith-number/XYR5XDGYMGAM5DZHRGOIZEIWY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYR5XDGYMGAM5DZHRGOIZEIWY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYR5XDGYMGAM5DZHRGOIZEIWY5/action/storage_attestation","attest_author":"https://pith.science/pith/XYR5XDGYMGAM5DZHRGOIZEIWY5/action/author_attestation","sign_citation":"https://pith.science/pith/XYR5XDGYMGAM5DZHRGOIZEIWY5/action/citation_signature","submit_replication":"https://pith.science/pith/XYR5XDGYMGAM5DZHRGOIZEIWY5/action/replication_record"}},"created_at":"2026-07-05T02:44:37.281550+00:00","updated_at":"2026-07-05T02:44:37.281550+00:00"}