{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TQ2UZROV2BK4EQXZKMTXXIR7RD","short_pith_number":"pith:TQ2UZROV","canonical_record":{"source":{"id":"2207.13331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-07-27T07:24:34Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"12a36638dc4364b4c5637bd156643af918511d6deb217cd60d6e5603661e779a","abstract_canon_sha256":"db4bb0f410ed6247751eb2ab90385a4be926a9773db0fc94e2e0df06aea62512"},"schema_version":"1.0"},"canonical_sha256":"9c354cc5d5d055c242f953277ba23f88fe0da843a20e2083992a8648351a7d21","source":{"kind":"arxiv","id":"2207.13331","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.13331","created_at":"2026-07-05T04:44:05Z"},{"alias_kind":"arxiv_version","alias_value":"2207.13331v1","created_at":"2026-07-05T04:44:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13331","created_at":"2026-07-05T04:44:05Z"},{"alias_kind":"pith_short_12","alias_value":"TQ2UZROV2BK4","created_at":"2026-07-05T04:44:05Z"},{"alias_kind":"pith_short_16","alias_value":"TQ2UZROV2BK4EQXZ","created_at":"2026-07-05T04:44:05Z"},{"alias_kind":"pith_short_8","alias_value":"TQ2UZROV","created_at":"2026-07-05T04:44:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TQ2UZROV2BK4EQXZKMTXXIR7RD","target":"record","payload":{"canonical_record":{"source":{"id":"2207.13331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-07-27T07:24:34Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"12a36638dc4364b4c5637bd156643af918511d6deb217cd60d6e5603661e779a","abstract_canon_sha256":"db4bb0f410ed6247751eb2ab90385a4be926a9773db0fc94e2e0df06aea62512"},"schema_version":"1.0"},"canonical_sha256":"9c354cc5d5d055c242f953277ba23f88fe0da843a20e2083992a8648351a7d21","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:05.674188Z","signature_b64":"VuhUuqb+VMo5uiZHz72NwV6mGOQO5EcdDesXXXzIjYbsWEB9tFAzowEqgg1SH1XyteA3fsK+2eL2n4KtaU6VDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c354cc5d5d055c242f953277ba23f88fe0da843a20e2083992a8648351a7d21","last_reissued_at":"2026-07-05T04:44:05.673735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:05.673735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.13331","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:44:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1aUGj6xnBv3IiEKHAFBpDhHcDxTrHyVHN9IhKYs1BUDFBX5icKpOkr0pEFYTuVcft9b7d9sy6jsx/xIyxgpWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T22:25:58.278066Z"},"content_sha256":"fd30dd77851237552634005fd7d87fe1f3393a4b604380fcede57ca7bbfdce55","schema_version":"1.0","event_id":"sha256:fd30dd77851237552634005fd7d87fe1f3393a4b604380fcede57ca7bbfdce55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TQ2UZROV2BK4EQXZKMTXXIR7RD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Subword Dictionary Learning and Segmentation Techniques for Automatic Speech Recognition in Tamil and Kannada","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bharathi Pilar, Madhavaraj A, Ramakrishnan A G","submitted_at":"2022-07-27T07:24:34Z","abstract_excerpt":"We present automatic speech recognition (ASR) systems for Tamil and Kannada based on subword modeling to effectively handle unlimited vocabulary due to the highly agglutinative nature of the languages. We explore byte pair encoding (BPE), and proposed a variant of this algorithm named extended-BPE, and Morfessor tool to segment each word as subwords. We have effectively incorporated maximum likelihood (ML) and Viterbi estimation techniques with weighted finite state transducers (WFST) framework in these algorithms to learn the subword dictionary from a large text corpus. Using the learnt subwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13331","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/2207.13331/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:44:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cIqFgvcWnwTt3EPM9oB84PTeHqDeRX1HmBRHQ0fzmXzpq5VSpeYiGlriY63/B0e6eJ6voLMr1Ko+DZZrJrrhAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T22:25:58.278557Z"},"content_sha256":"a2f0b8bddfe15b76f3e43cab08abd48088586c597be1f5e050a24a1feef2b5f1","schema_version":"1.0","event_id":"sha256:a2f0b8bddfe15b76f3e43cab08abd48088586c597be1f5e050a24a1feef2b5f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TQ2UZROV2BK4EQXZKMTXXIR7RD/bundle.json","state_url":"https://pith.science/pith/TQ2UZROV2BK4EQXZKMTXXIR7RD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TQ2UZROV2BK4EQXZKMTXXIR7RD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T22:25:58Z","links":{"resolver":"https://pith.science/pith/TQ2UZROV2BK4EQXZKMTXXIR7RD","bundle":"https://pith.science/pith/TQ2UZROV2BK4EQXZKMTXXIR7RD/bundle.json","state":"https://pith.science/pith/TQ2UZROV2BK4EQXZKMTXXIR7RD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TQ2UZROV2BK4EQXZKMTXXIR7RD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TQ2UZROV2BK4EQXZKMTXXIR7RD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"db4bb0f410ed6247751eb2ab90385a4be926a9773db0fc94e2e0df06aea62512","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-07-27T07:24:34Z","title_canon_sha256":"12a36638dc4364b4c5637bd156643af918511d6deb217cd60d6e5603661e779a"},"schema_version":"1.0","source":{"id":"2207.13331","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.13331","created_at":"2026-07-05T04:44:05Z"},{"alias_kind":"arxiv_version","alias_value":"2207.13331v1","created_at":"2026-07-05T04:44:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13331","created_at":"2026-07-05T04:44:05Z"},{"alias_kind":"pith_short_12","alias_value":"TQ2UZROV2BK4","created_at":"2026-07-05T04:44:05Z"},{"alias_kind":"pith_short_16","alias_value":"TQ2UZROV2BK4EQXZ","created_at":"2026-07-05T04:44:05Z"},{"alias_kind":"pith_short_8","alias_value":"TQ2UZROV","created_at":"2026-07-05T04:44:05Z"}],"graph_snapshots":[{"event_id":"sha256:a2f0b8bddfe15b76f3e43cab08abd48088586c597be1f5e050a24a1feef2b5f1","target":"graph","created_at":"2026-07-05T04:44:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2207.13331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present automatic speech recognition (ASR) systems for Tamil and Kannada based on subword modeling to effectively handle unlimited vocabulary due to the highly agglutinative nature of the languages. We explore byte pair encoding (BPE), and proposed a variant of this algorithm named extended-BPE, and Morfessor tool to segment each word as subwords. We have effectively incorporated maximum likelihood (ML) and Viterbi estimation techniques with weighted finite state transducers (WFST) framework in these algorithms to learn the subword dictionary from a large text corpus. Using the learnt subwo","authors_text":"Bharathi Pilar, Madhavaraj A, Ramakrishnan A G","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-07-27T07:24:34Z","title":"Subword Dictionary Learning and Segmentation Techniques for Automatic Speech Recognition in Tamil and Kannada"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13331","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fd30dd77851237552634005fd7d87fe1f3393a4b604380fcede57ca7bbfdce55","target":"record","created_at":"2026-07-05T04:44:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"db4bb0f410ed6247751eb2ab90385a4be926a9773db0fc94e2e0df06aea62512","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-07-27T07:24:34Z","title_canon_sha256":"12a36638dc4364b4c5637bd156643af918511d6deb217cd60d6e5603661e779a"},"schema_version":"1.0","source":{"id":"2207.13331","kind":"arxiv","version":1}},"canonical_sha256":"9c354cc5d5d055c242f953277ba23f88fe0da843a20e2083992a8648351a7d21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c354cc5d5d055c242f953277ba23f88fe0da843a20e2083992a8648351a7d21","first_computed_at":"2026-07-05T04:44:05.673735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:44:05.673735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VuhUuqb+VMo5uiZHz72NwV6mGOQO5EcdDesXXXzIjYbsWEB9tFAzowEqgg1SH1XyteA3fsK+2eL2n4KtaU6VDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:44:05.674188Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.13331","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd30dd77851237552634005fd7d87fe1f3393a4b604380fcede57ca7bbfdce55","sha256:a2f0b8bddfe15b76f3e43cab08abd48088586c597be1f5e050a24a1feef2b5f1"],"state_sha256":"d3f11825bd64e3a1c2ae1eb649bf14f73cbf943528f9d258aa28fe26ec1e2536"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rd1MrVPM053h0uG9EAJZlFLSTxlaQIEuTfbrHI2jOJtmAAehFehI3h/N8ZCEN0WBK01fu6ltiugeGfk3hoVOBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T22:25:58.282053Z","bundle_sha256":"863ae63a1adf91bc3bd162ce20fe8bb55850e54c4208a23e465e242f3bbbf798"}}