{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6SM5RDFHKUZMI2KD7QCGWMHTPS","short_pith_number":"pith:6SM5RDFH","schema_version":"1.0","canonical_sha256":"f499d88ca75532c46943fc046b30f37ca898c3dd261b3274840db9d770088927","source":{"kind":"arxiv","id":"2106.01400","version":1},"attestation_state":"computed","paper":{"title":"Dual Script E2E framework for Multilingual and Code-Switching ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Anand Thyagachandran, Anusha Prakash, Arun Kumar A, Ashish Seth, Hema Murthy, Jom Kuriakose, Lodagala Durga Prasad, Mari Ganesh Kumar, Saish Jaiswal","submitted_at":"2021-06-02T18:08:27Z","abstract_excerpt":"India is home to multiple languages, and training automatic speech recognition (ASR) systems for languages is challenging. Over time, each language has adopted words from other languages, such as English, leading to code-mixing. Most Indian languages also have their own unique scripts, which poses a major limitation in training multilingual and code-switching ASR systems.\n  Inspired by results in text-to-speech synthesis, in this work, we use an in-house rule-based phoneme-level common label set (CLS) representation to train multilingual and code-switching ASR for Indian languages. We 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":"2106.01400","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-02T18:08:27Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"d173e9ee481f84fa30662b112645fcdd157b947fdafab9f75a2b3b96b4694871","abstract_canon_sha256":"20b16ed1417276197bed0b8b4de8b3f3c9866a0367ec50e69b84a5fc9a7355b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:50.967291Z","signature_b64":"mlL/QpojeGdKEwpA2SbiiNeOqHr+0YgMwAmdXN8DrPDrNQw4yix6Q1GwiIhqbY1T1vqNqv/dIBGADmbpEC61Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f499d88ca75532c46943fc046b30f37ca898c3dd261b3274840db9d770088927","last_reissued_at":"2026-07-05T02:45:50.966767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:50.966767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Script E2E framework for Multilingual and Code-Switching ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Anand Thyagachandran, Anusha Prakash, Arun Kumar A, Ashish Seth, Hema Murthy, Jom Kuriakose, Lodagala Durga Prasad, Mari Ganesh Kumar, Saish Jaiswal","submitted_at":"2021-06-02T18:08:27Z","abstract_excerpt":"India is home to multiple languages, and training automatic speech recognition (ASR) systems for languages is challenging. Over time, each language has adopted words from other languages, such as English, leading to code-mixing. Most Indian languages also have their own unique scripts, which poses a major limitation in training multilingual and code-switching ASR systems.\n  Inspired by results in text-to-speech synthesis, in this work, we use an in-house rule-based phoneme-level common label set (CLS) representation to train multilingual and code-switching ASR for Indian languages. We propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01400","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/2106.01400/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":"2106.01400","created_at":"2026-07-05T02:45:50.966831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.01400v1","created_at":"2026-07-05T02:45:50.966831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01400","created_at":"2026-07-05T02:45:50.966831+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SM5RDFHKUZM","created_at":"2026-07-05T02:45:50.966831+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SM5RDFHKUZMI2KD","created_at":"2026-07-05T02:45:50.966831+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SM5RDFH","created_at":"2026-07-05T02:45:50.966831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17826","citing_title":"When Multiple Scripts Matter: Evaluating ASR in Clinical Settings","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6SM5RDFHKUZMI2KD7QCGWMHTPS","json":"https://pith.science/pith/6SM5RDFHKUZMI2KD7QCGWMHTPS.json","graph_json":"https://pith.science/api/pith-number/6SM5RDFHKUZMI2KD7QCGWMHTPS/graph.json","events_json":"https://pith.science/api/pith-number/6SM5RDFHKUZMI2KD7QCGWMHTPS/events.json","paper":"https://pith.science/paper/6SM5RDFH"},"agent_actions":{"view_html":"https://pith.science/pith/6SM5RDFHKUZMI2KD7QCGWMHTPS","download_json":"https://pith.science/pith/6SM5RDFHKUZMI2KD7QCGWMHTPS.json","view_paper":"https://pith.science/paper/6SM5RDFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.01400&json=true","fetch_graph":"https://pith.science/api/pith-number/6SM5RDFHKUZMI2KD7QCGWMHTPS/graph.json","fetch_events":"https://pith.science/api/pith-number/6SM5RDFHKUZMI2KD7QCGWMHTPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SM5RDFHKUZMI2KD7QCGWMHTPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SM5RDFHKUZMI2KD7QCGWMHTPS/action/storage_attestation","attest_author":"https://pith.science/pith/6SM5RDFHKUZMI2KD7QCGWMHTPS/action/author_attestation","sign_citation":"https://pith.science/pith/6SM5RDFHKUZMI2KD7QCGWMHTPS/action/citation_signature","submit_replication":"https://pith.science/pith/6SM5RDFHKUZMI2KD7QCGWMHTPS/action/replication_record"}},"created_at":"2026-07-05T02:45:50.966831+00:00","updated_at":"2026-07-05T02:45:50.966831+00:00"}