{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:L3IALUKLXH2YPA5M3YTIFOO2XU","short_pith_number":"pith:L3IALUKL","schema_version":"1.0","canonical_sha256":"5ed005d14bb9f58783acde2682b9dabd364046924c3c54d951ebfb102e2e148b","source":{"kind":"arxiv","id":"2211.12796","version":1},"attestation_state":"computed","paper":{"title":"IMaSC -- ICFOSS Malayalam Speech Corpus","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Deepa P Gopinath, Sachin G, Swaraj K S, Thennal D K, Vrinda V Nair","submitted_at":"2022-11-23T09:21:01Z","abstract_excerpt":"Modern text-to-speech (TTS) systems use deep learning to synthesize speech increasingly approaching human quality, but they require a database of high quality audio-text sentence pairs for training. Malayalam, the official language of the Indian state of Kerala and spoken by 35+ million people, is a low resource language in terms of available corpora for TTS systems. In this paper, we present IMaSC, a Malayalam text and speech corpora containing approximately 50 hours of recorded speech. With 8 speakers and a total of 34,473 text-audio pairs, IMaSC is larger than every other publicly available"},"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":"2211.12796","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-23T09:21:01Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"d7870c1118018f6fa3a74a6742d85c691c05c6e97e4d80d2d8b27961857be048","abstract_canon_sha256":"54c1052655ce76599788903b002460ffbe672dae56a5e4d18ad8b42ae6b3552e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:55.258596Z","signature_b64":"QqtCnA3/IvFgm/bNlFdXTMYKOTKKyOqzPhlcxV9ihXEFg5RFl0waZb5imkt6wRQ+xHJpw6NltUZM4hFo28m+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ed005d14bb9f58783acde2682b9dabd364046924c3c54d951ebfb102e2e148b","last_reissued_at":"2026-07-05T05:18:55.257286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:55.257286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IMaSC -- ICFOSS Malayalam Speech Corpus","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Deepa P Gopinath, Sachin G, Swaraj K S, Thennal D K, Vrinda V Nair","submitted_at":"2022-11-23T09:21:01Z","abstract_excerpt":"Modern text-to-speech (TTS) systems use deep learning to synthesize speech increasingly approaching human quality, but they require a database of high quality audio-text sentence pairs for training. Malayalam, the official language of the Indian state of Kerala and spoken by 35+ million people, is a low resource language in terms of available corpora for TTS systems. In this paper, we present IMaSC, a Malayalam text and speech corpora containing approximately 50 hours of recorded speech. With 8 speakers and a total of 34,473 text-audio pairs, IMaSC is larger than every other publicly available"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12796","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/2211.12796/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":"2211.12796","created_at":"2026-07-05T05:18:55.257847+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12796v1","created_at":"2026-07-05T05:18:55.257847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12796","created_at":"2026-07-05T05:18:55.257847+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3IALUKLXH2Y","created_at":"2026-07-05T05:18:55.257847+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3IALUKLXH2YPA5M","created_at":"2026-07-05T05:18:55.257847+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3IALUKL","created_at":"2026-07-05T05:18:55.257847+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20712","citing_title":"SCRIBE: Diagnostic Evaluation and Rich Transcription Models for Indic ASR","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20712","citing_title":"SCRIBE: Diagnostic Evaluation and Rich Transcription Models for Indic ASR","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L3IALUKLXH2YPA5M3YTIFOO2XU","json":"https://pith.science/pith/L3IALUKLXH2YPA5M3YTIFOO2XU.json","graph_json":"https://pith.science/api/pith-number/L3IALUKLXH2YPA5M3YTIFOO2XU/graph.json","events_json":"https://pith.science/api/pith-number/L3IALUKLXH2YPA5M3YTIFOO2XU/events.json","paper":"https://pith.science/paper/L3IALUKL"},"agent_actions":{"view_html":"https://pith.science/pith/L3IALUKLXH2YPA5M3YTIFOO2XU","download_json":"https://pith.science/pith/L3IALUKLXH2YPA5M3YTIFOO2XU.json","view_paper":"https://pith.science/paper/L3IALUKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12796&json=true","fetch_graph":"https://pith.science/api/pith-number/L3IALUKLXH2YPA5M3YTIFOO2XU/graph.json","fetch_events":"https://pith.science/api/pith-number/L3IALUKLXH2YPA5M3YTIFOO2XU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3IALUKLXH2YPA5M3YTIFOO2XU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3IALUKLXH2YPA5M3YTIFOO2XU/action/storage_attestation","attest_author":"https://pith.science/pith/L3IALUKLXH2YPA5M3YTIFOO2XU/action/author_attestation","sign_citation":"https://pith.science/pith/L3IALUKLXH2YPA5M3YTIFOO2XU/action/citation_signature","submit_replication":"https://pith.science/pith/L3IALUKLXH2YPA5M3YTIFOO2XU/action/replication_record"}},"created_at":"2026-07-05T05:18:55.257847+00:00","updated_at":"2026-07-05T05:18:55.257847+00:00"}