{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2SBOTSAFQUXRN3B7CH3ZP55E5N","short_pith_number":"pith:2SBOTSAF","schema_version":"1.0","canonical_sha256":"d482e9c805852f16ec3f11f797f7a4eb546d5225c9953992f882646783381112","source":{"kind":"arxiv","id":"2110.12561","version":1},"attestation_state":"computed","paper":{"title":"Lhotse: a speech data representation library for the modern deep learning ecosystem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Daniel Povey, Jan \"Yenda\" Trmal, Piotr \\.Zelasko, Sanjeev Khudanpur","submitted_at":"2021-10-25T00:32:21Z","abstract_excerpt":"Speech data is notoriously difficult to work with due to a variety of codecs, lengths of recordings, and meta-data formats. We present Lhotse, a speech data representation library that draws upon lessons learned from Kaldi speech recognition toolkit and brings its concepts into the modern deep learning ecosystem. Lhotse provides a common JSON description format with corresponding Python classes and data preparation recipes for over 30 popular speech corpora. Various datasets can be easily combined together and re-purposed for different tasks. The library handles multi-channel recordings, long "},"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":"2110.12561","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-25T00:32:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"3f63db4a5c118e123728c6d6042ba33b27c791ef804db9a852361486c6dc7a50","abstract_canon_sha256":"3e944ebc1c3e352dec8f1549e54f825893a427d39e27f23fd9b4f327e32aac53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:21.608148Z","signature_b64":"2eQ1DzaqNSuFzCgzuSGuFGZO2uz2QTbDQz2dngA7Aiz4iB6sbRBVc//c8eur6mOVoMmgJT6+d8xEbAQLmBL8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d482e9c805852f16ec3f11f797f7a4eb546d5225c9953992f882646783381112","last_reissued_at":"2026-07-05T03:25:21.607730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:21.607730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lhotse: a speech data representation library for the modern deep learning ecosystem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Daniel Povey, Jan \"Yenda\" Trmal, Piotr \\.Zelasko, Sanjeev Khudanpur","submitted_at":"2021-10-25T00:32:21Z","abstract_excerpt":"Speech data is notoriously difficult to work with due to a variety of codecs, lengths of recordings, and meta-data formats. We present Lhotse, a speech data representation library that draws upon lessons learned from Kaldi speech recognition toolkit and brings its concepts into the modern deep learning ecosystem. Lhotse provides a common JSON description format with corresponding Python classes and data preparation recipes for over 30 popular speech corpora. Various datasets can be easily combined together and re-purposed for different tasks. The library handles multi-channel recordings, long "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12561","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/2110.12561/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":"2110.12561","created_at":"2026-07-05T03:25:21.607788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.12561v1","created_at":"2026-07-05T03:25:21.607788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12561","created_at":"2026-07-05T03:25:21.607788+00:00"},{"alias_kind":"pith_short_12","alias_value":"2SBOTSAFQUXR","created_at":"2026-07-05T03:25:21.607788+00:00"},{"alias_kind":"pith_short_16","alias_value":"2SBOTSAFQUXRN3B7","created_at":"2026-07-05T03:25:21.607788+00:00"},{"alias_kind":"pith_short_8","alias_value":"2SBOTSAF","created_at":"2026-07-05T03:25:21.607788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15442","citing_title":"Mind the Gap: Impact of Synthetic Conversational Data on Multi-Talker ASR and Speaker Diarization","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N","json":"https://pith.science/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N.json","graph_json":"https://pith.science/api/pith-number/2SBOTSAFQUXRN3B7CH3ZP55E5N/graph.json","events_json":"https://pith.science/api/pith-number/2SBOTSAFQUXRN3B7CH3ZP55E5N/events.json","paper":"https://pith.science/paper/2SBOTSAF"},"agent_actions":{"view_html":"https://pith.science/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N","download_json":"https://pith.science/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N.json","view_paper":"https://pith.science/paper/2SBOTSAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.12561&json=true","fetch_graph":"https://pith.science/api/pith-number/2SBOTSAFQUXRN3B7CH3ZP55E5N/graph.json","fetch_events":"https://pith.science/api/pith-number/2SBOTSAFQUXRN3B7CH3ZP55E5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N/action/storage_attestation","attest_author":"https://pith.science/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N/action/author_attestation","sign_citation":"https://pith.science/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N/action/citation_signature","submit_replication":"https://pith.science/pith/2SBOTSAFQUXRN3B7CH3ZP55E5N/action/replication_record"}},"created_at":"2026-07-05T03:25:21.607788+00:00","updated_at":"2026-07-05T03:25:21.607788+00:00"}