{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EMGQGM7XCWI4CBADBILN2F6PJ4","short_pith_number":"pith:EMGQGM7X","schema_version":"1.0","canonical_sha256":"230d0333f71591c104030a16dd17cf4f0b89fd478189b3f334f6514e7740cc2e","source":{"kind":"arxiv","id":"2607.01594","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Acoustic-to-Articulatory Inversion with Multi-Target Pretraining for Low-Resource Settings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Jesuraj Bandekar, Prasanta Kumar Ghosh","submitted_at":"2026-07-02T01:43:57Z","abstract_excerpt":"Acoustic-to-Articulatory Inversion (AAI) estimates vocal tract articulator movements from speech, benefiting tasks like ASR, speech synthesis, and speaker verification. While deep learning-based methods (CNNs, RNNs, Transformers) have advanced AAI, recent studies show that Self-Supervised Learning (SSL) features further enhance performance, particularly in low-resource settings. However, SSL feature extractors introduce inference latency and computational overhead. To address this, we propose a novel pretraining method leveraging three target representations-Phoneme Labels, Articulatory Featur"},"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":"2607.01594","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-02T01:43:57Z","cross_cats_sorted":[],"title_canon_sha256":"487774439388e02f2f0c842bf680462349dba48b0dd4230c83f810daa01e8820","abstract_canon_sha256":"5dfe12cf579912ef7cb543682d106734296c01e3a2fdb12ae4c3ae91ecf956b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:02.843193Z","signature_b64":"zWeYpaou12ORia5nZcqwpKfwed/Llb70+em9HMRrOH6FvB6+dT1n3Wg/K8+V2GeESrG08jVBth6K9zsLmC5xDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"230d0333f71591c104030a16dd17cf4f0b89fd478189b3f334f6514e7740cc2e","last_reissued_at":"2026-07-03T01:17:02.842786Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:02.842786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Acoustic-to-Articulatory Inversion with Multi-Target Pretraining for Low-Resource Settings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Jesuraj Bandekar, Prasanta Kumar Ghosh","submitted_at":"2026-07-02T01:43:57Z","abstract_excerpt":"Acoustic-to-Articulatory Inversion (AAI) estimates vocal tract articulator movements from speech, benefiting tasks like ASR, speech synthesis, and speaker verification. While deep learning-based methods (CNNs, RNNs, Transformers) have advanced AAI, recent studies show that Self-Supervised Learning (SSL) features further enhance performance, particularly in low-resource settings. However, SSL feature extractors introduce inference latency and computational overhead. To address this, we propose a novel pretraining method leveraging three target representations-Phoneme Labels, Articulatory Featur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01594","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/2607.01594/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":"2607.01594","created_at":"2026-07-03T01:17:02.842843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01594v1","created_at":"2026-07-03T01:17:02.842843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01594","created_at":"2026-07-03T01:17:02.842843+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMGQGM7XCWI4","created_at":"2026-07-03T01:17:02.842843+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMGQGM7XCWI4CBAD","created_at":"2026-07-03T01:17:02.842843+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMGQGM7X","created_at":"2026-07-03T01:17:02.842843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.01594","citing_title":"Enhancing Acoustic-to-Articulatory Inversion with Multi-Target Pretraining for Low-Resource Settings","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMGQGM7XCWI4CBADBILN2F6PJ4","json":"https://pith.science/pith/EMGQGM7XCWI4CBADBILN2F6PJ4.json","graph_json":"https://pith.science/api/pith-number/EMGQGM7XCWI4CBADBILN2F6PJ4/graph.json","events_json":"https://pith.science/api/pith-number/EMGQGM7XCWI4CBADBILN2F6PJ4/events.json","paper":"https://pith.science/paper/EMGQGM7X"},"agent_actions":{"view_html":"https://pith.science/pith/EMGQGM7XCWI4CBADBILN2F6PJ4","download_json":"https://pith.science/pith/EMGQGM7XCWI4CBADBILN2F6PJ4.json","view_paper":"https://pith.science/paper/EMGQGM7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01594&json=true","fetch_graph":"https://pith.science/api/pith-number/EMGQGM7XCWI4CBADBILN2F6PJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/EMGQGM7XCWI4CBADBILN2F6PJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMGQGM7XCWI4CBADBILN2F6PJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMGQGM7XCWI4CBADBILN2F6PJ4/action/storage_attestation","attest_author":"https://pith.science/pith/EMGQGM7XCWI4CBADBILN2F6PJ4/action/author_attestation","sign_citation":"https://pith.science/pith/EMGQGM7XCWI4CBADBILN2F6PJ4/action/citation_signature","submit_replication":"https://pith.science/pith/EMGQGM7XCWI4CBADBILN2F6PJ4/action/replication_record"}},"created_at":"2026-07-03T01:17:02.842843+00:00","updated_at":"2026-07-03T01:17:02.842843+00:00"}