{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6GPSZJ5TAZBOLQLYSJBLIXM2TD","short_pith_number":"pith:6GPSZJ5T","schema_version":"1.0","canonical_sha256":"f19f2ca7b30642e5c1789242b45d9a98cafcfafc156fb3ee16112f0bded22935","source":{"kind":"arxiv","id":"1906.05678","version":1},"attestation_state":"computed","paper":{"title":"Telephonetic: Making Neural Language Models Robust to ASR and Semantic Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Chris Larson, Diana Mingels, Erik Mueller, Tarek Lahlou, Zachary Kulis","submitted_at":"2019-06-13T17:04:46Z","abstract_excerpt":"Speech processing systems rely on robust feature extraction to handle phonetic and semantic variations found in natural language. While techniques exist for desensitizing features to common noise patterns produced by Speech-to-Text (STT) and Text-to-Speech (TTS) systems, the question remains how to best leverage state-of-the-art language models (which capture rich semantic features, but are trained on only written text) on inputs with ASR errors. In this paper, we present Telephonetic, a data augmentation framework that helps robustify language model features to ASR corrupted inputs. To captur"},"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":"1906.05678","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-06-13T17:04:46Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"8a8552953baa58ef72e44bda94746f4edd539cb0c622513568bf9efe77ff3bb3","abstract_canon_sha256":"06564270f4bcdfd4829a843db17454d18c9b25350beea3b08639a103c24ca860"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:24.628197Z","signature_b64":"EBl0dffyrjlRkNNSEaeEeXc6HyJsdy/OJs8ZQh25CUXqyZ8f/PNqX/KKSOgLUkRq6JVClJBCCR/M+/sKOGykCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f19f2ca7b30642e5c1789242b45d9a98cafcfafc156fb3ee16112f0bded22935","last_reissued_at":"2026-05-17T23:43:24.627794Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:24.627794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Telephonetic: Making Neural Language Models Robust to ASR and Semantic Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Chris Larson, Diana Mingels, Erik Mueller, Tarek Lahlou, Zachary Kulis","submitted_at":"2019-06-13T17:04:46Z","abstract_excerpt":"Speech processing systems rely on robust feature extraction to handle phonetic and semantic variations found in natural language. While techniques exist for desensitizing features to common noise patterns produced by Speech-to-Text (STT) and Text-to-Speech (TTS) systems, the question remains how to best leverage state-of-the-art language models (which capture rich semantic features, but are trained on only written text) on inputs with ASR errors. In this paper, we present Telephonetic, a data augmentation framework that helps robustify language model features to ASR corrupted inputs. To captur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05678","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":""},"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":"1906.05678","created_at":"2026-05-17T23:43:24.627860+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05678v1","created_at":"2026-05-17T23:43:24.627860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05678","created_at":"2026-05-17T23:43:24.627860+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GPSZJ5TAZBO","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GPSZJ5TAZBOLQLY","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GPSZJ5T","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GPSZJ5TAZBOLQLYSJBLIXM2TD","json":"https://pith.science/pith/6GPSZJ5TAZBOLQLYSJBLIXM2TD.json","graph_json":"https://pith.science/api/pith-number/6GPSZJ5TAZBOLQLYSJBLIXM2TD/graph.json","events_json":"https://pith.science/api/pith-number/6GPSZJ5TAZBOLQLYSJBLIXM2TD/events.json","paper":"https://pith.science/paper/6GPSZJ5T"},"agent_actions":{"view_html":"https://pith.science/pith/6GPSZJ5TAZBOLQLYSJBLIXM2TD","download_json":"https://pith.science/pith/6GPSZJ5TAZBOLQLYSJBLIXM2TD.json","view_paper":"https://pith.science/paper/6GPSZJ5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05678&json=true","fetch_graph":"https://pith.science/api/pith-number/6GPSZJ5TAZBOLQLYSJBLIXM2TD/graph.json","fetch_events":"https://pith.science/api/pith-number/6GPSZJ5TAZBOLQLYSJBLIXM2TD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GPSZJ5TAZBOLQLYSJBLIXM2TD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GPSZJ5TAZBOLQLYSJBLIXM2TD/action/storage_attestation","attest_author":"https://pith.science/pith/6GPSZJ5TAZBOLQLYSJBLIXM2TD/action/author_attestation","sign_citation":"https://pith.science/pith/6GPSZJ5TAZBOLQLYSJBLIXM2TD/action/citation_signature","submit_replication":"https://pith.science/pith/6GPSZJ5TAZBOLQLYSJBLIXM2TD/action/replication_record"}},"created_at":"2026-05-17T23:43:24.627860+00:00","updated_at":"2026-05-17T23:43:24.627860+00:00"}