{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RLNPR3KWVTF6OC3FGFLTBVMC2C","short_pith_number":"pith:RLNPR3KW","schema_version":"1.0","canonical_sha256":"8adaf8ed56accbe70b65315730d582d08ca88cd17d89970562265cf1a4c6fd2c","source":{"kind":"arxiv","id":"2205.13755","version":1},"attestation_state":"computed","paper":{"title":"Acoustic-to-articulatory Speech Inversion with Multi-task Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Carol Espy-Wilson, Ganesh Sivaraman, Yashish M. Siriwardena","submitted_at":"2022-05-27T03:52:25Z","abstract_excerpt":"Multi-task learning (MTL) frameworks have proven to be effective in diverse speech related tasks like automatic speech recognition (ASR) and speech emotion recognition. This paper proposes a MTL framework to perform acoustic-to-articulatory speech inversion by simultaneously learning an acoustic to phoneme mapping as a shared task. We use the Haskins Production Rate Comparison (HPRC) database which has both the electromagnetic articulography (EMA) data and the corresponding phonetic transcriptions. Performance of the system was measured by computing the correlation between estimated and actual"},"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":"2205.13755","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-05-27T03:52:25Z","cross_cats_sorted":[],"title_canon_sha256":"f60ec4705568ea08d32a8bcb0e30b1daa3280d19cd911b9f4208a14529eebe6a","abstract_canon_sha256":"05e6dabb7e89fd690a2a09ee4e2ddced0a57b82ac5804034041d89683873aa85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:00.471493Z","signature_b64":"DZPDwpdR6XCGBgNl3xRoXr4cIMVNu+xacMczOaXDS+mn77HrAuCt6m+tPKx8VYGxpQM3Xvlsh8L/QAoD9v4CCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8adaf8ed56accbe70b65315730d582d08ca88cd17d89970562265cf1a4c6fd2c","last_reissued_at":"2026-07-05T06:11:00.471056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:00.471056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Acoustic-to-articulatory Speech Inversion with Multi-task Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Carol Espy-Wilson, Ganesh Sivaraman, Yashish M. Siriwardena","submitted_at":"2022-05-27T03:52:25Z","abstract_excerpt":"Multi-task learning (MTL) frameworks have proven to be effective in diverse speech related tasks like automatic speech recognition (ASR) and speech emotion recognition. This paper proposes a MTL framework to perform acoustic-to-articulatory speech inversion by simultaneously learning an acoustic to phoneme mapping as a shared task. We use the Haskins Production Rate Comparison (HPRC) database which has both the electromagnetic articulography (EMA) data and the corresponding phonetic transcriptions. Performance of the system was measured by computing the correlation between estimated and actual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13755","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/2205.13755/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":"2205.13755","created_at":"2026-07-05T06:11:00.471111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.13755v1","created_at":"2026-07-05T06:11:00.471111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13755","created_at":"2026-07-05T06:11:00.471111+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLNPR3KWVTF6","created_at":"2026-07-05T06:11:00.471111+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLNPR3KWVTF6OC3F","created_at":"2026-07-05T06:11:00.471111+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLNPR3KW","created_at":"2026-07-05T06:11:00.471111+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01594","citing_title":"Enhancing Acoustic-to-Articulatory Inversion with Multi-Target Pretraining for Low-Resource Settings","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RLNPR3KWVTF6OC3FGFLTBVMC2C","json":"https://pith.science/pith/RLNPR3KWVTF6OC3FGFLTBVMC2C.json","graph_json":"https://pith.science/api/pith-number/RLNPR3KWVTF6OC3FGFLTBVMC2C/graph.json","events_json":"https://pith.science/api/pith-number/RLNPR3KWVTF6OC3FGFLTBVMC2C/events.json","paper":"https://pith.science/paper/RLNPR3KW"},"agent_actions":{"view_html":"https://pith.science/pith/RLNPR3KWVTF6OC3FGFLTBVMC2C","download_json":"https://pith.science/pith/RLNPR3KWVTF6OC3FGFLTBVMC2C.json","view_paper":"https://pith.science/paper/RLNPR3KW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.13755&json=true","fetch_graph":"https://pith.science/api/pith-number/RLNPR3KWVTF6OC3FGFLTBVMC2C/graph.json","fetch_events":"https://pith.science/api/pith-number/RLNPR3KWVTF6OC3FGFLTBVMC2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLNPR3KWVTF6OC3FGFLTBVMC2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLNPR3KWVTF6OC3FGFLTBVMC2C/action/storage_attestation","attest_author":"https://pith.science/pith/RLNPR3KWVTF6OC3FGFLTBVMC2C/action/author_attestation","sign_citation":"https://pith.science/pith/RLNPR3KWVTF6OC3FGFLTBVMC2C/action/citation_signature","submit_replication":"https://pith.science/pith/RLNPR3KWVTF6OC3FGFLTBVMC2C/action/replication_record"}},"created_at":"2026-07-05T06:11:00.471111+00:00","updated_at":"2026-07-05T06:11:00.471111+00:00"}