{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:66QAYZKK7PAPROPHCLCU6BAV63","short_pith_number":"pith:66QAYZKK","schema_version":"1.0","canonical_sha256":"f7a00c654afbc0f8b9e712c54f0415f6e49f66ff3b6a24e4ef4afbf16abe2c42","source":{"kind":"arxiv","id":"2205.13086","version":3},"attestation_state":"computed","paper":{"title":"Audio Data Augmentation for Acoustic-to-articulatory Speech Inversion using Bidirectional Gated RNNs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ahmed Adel Attia, Carol Espy-Wilson, Ganesh Sivaraman, Yashish M. Siriwardena","submitted_at":"2022-05-25T23:57:15Z","abstract_excerpt":"Data augmentation has proven to be a promising prospect in improving the performance of deep learning models by adding variability to training data. In previous work with developing a noise robust acoustic-to-articulatory speech inversion system, we have shown the importance of noise augmentation to improve the performance of speech inversion in noisy speech. In this work, we compare and contrast different ways of doing data augmentation and show how this technique improves the performance of articulatory speech inversion not only on noisy speech, but also on clean speech data. We also propose"},"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":"2205.13086","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-05-25T23:57:15Z","cross_cats_sorted":[],"title_canon_sha256":"65e5389e0c35307c01f1bc381e86fddf965fe8f6e839bfd16569681460d70ef2","abstract_canon_sha256":"7abda141f71236e725f0b99e8fefcd422840cab3aa6512258738e51e48fb76a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:10.427108Z","signature_b64":"Gg3Jms0cDkTipcuZy5dlEWornpOEWB3p+rMIzBjmbwTQZqFn01AmaOSIJw8KQ+RFiDDuOoNhHUP/7B56Tqp1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7a00c654afbc0f8b9e712c54f0415f6e49f66ff3b6a24e4ef4afbf16abe2c42","last_reissued_at":"2026-07-05T06:16:10.426646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:10.426646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio Data Augmentation for Acoustic-to-articulatory Speech Inversion using Bidirectional Gated RNNs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ahmed Adel Attia, Carol Espy-Wilson, Ganesh Sivaraman, Yashish M. Siriwardena","submitted_at":"2022-05-25T23:57:15Z","abstract_excerpt":"Data augmentation has proven to be a promising prospect in improving the performance of deep learning models by adding variability to training data. In previous work with developing a noise robust acoustic-to-articulatory speech inversion system, we have shown the importance of noise augmentation to improve the performance of speech inversion in noisy speech. In this work, we compare and contrast different ways of doing data augmentation and show how this technique improves the performance of articulatory speech inversion not only on noisy speech, but also on clean speech data. We also propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13086","kind":"arxiv","version":3},"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/2205.13086/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":"2205.13086","created_at":"2026-07-05T06:16:10.426704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.13086v3","created_at":"2026-07-05T06:16:10.426704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13086","created_at":"2026-07-05T06:16:10.426704+00:00"},{"alias_kind":"pith_short_12","alias_value":"66QAYZKK7PAP","created_at":"2026-07-05T06:16:10.426704+00:00"},{"alias_kind":"pith_short_16","alias_value":"66QAYZKK7PAPROPH","created_at":"2026-07-05T06:16:10.426704+00:00"},{"alias_kind":"pith_short_8","alias_value":"66QAYZKK","created_at":"2026-07-05T06:16:10.426704+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":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66QAYZKK7PAPROPHCLCU6BAV63","json":"https://pith.science/pith/66QAYZKK7PAPROPHCLCU6BAV63.json","graph_json":"https://pith.science/api/pith-number/66QAYZKK7PAPROPHCLCU6BAV63/graph.json","events_json":"https://pith.science/api/pith-number/66QAYZKK7PAPROPHCLCU6BAV63/events.json","paper":"https://pith.science/paper/66QAYZKK"},"agent_actions":{"view_html":"https://pith.science/pith/66QAYZKK7PAPROPHCLCU6BAV63","download_json":"https://pith.science/pith/66QAYZKK7PAPROPHCLCU6BAV63.json","view_paper":"https://pith.science/paper/66QAYZKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.13086&json=true","fetch_graph":"https://pith.science/api/pith-number/66QAYZKK7PAPROPHCLCU6BAV63/graph.json","fetch_events":"https://pith.science/api/pith-number/66QAYZKK7PAPROPHCLCU6BAV63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66QAYZKK7PAPROPHCLCU6BAV63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66QAYZKK7PAPROPHCLCU6BAV63/action/storage_attestation","attest_author":"https://pith.science/pith/66QAYZKK7PAPROPHCLCU6BAV63/action/author_attestation","sign_citation":"https://pith.science/pith/66QAYZKK7PAPROPHCLCU6BAV63/action/citation_signature","submit_replication":"https://pith.science/pith/66QAYZKK7PAPROPHCLCU6BAV63/action/replication_record"}},"created_at":"2026-07-05T06:16:10.426704+00:00","updated_at":"2026-07-05T06:16:10.426704+00:00"}