{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WXV7YSPK7HUTVGENDPKTPKRBE6","short_pith_number":"pith:WXV7YSPK","schema_version":"1.0","canonical_sha256":"b5ebfc49eaf9e93a988d1bd537aa21278bd9f94fdbb631ab0fc7b8de909602fc","source":{"kind":"arxiv","id":"2108.02625","version":1},"attestation_state":"computed","paper":{"title":"MSTRE-Net: Multistreaming Acoustic Modeling for Automatic Lyrics Transcription","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR","eess.AS"],"primary_cat":"cs.SD","authors_text":"Emir Demirel, Simon Dixon, Sven Ahlb\\\"ack","submitted_at":"2021-08-05T13:59:11Z","abstract_excerpt":"This paper makes several contributions to automatic lyrics transcription (ALT) research. Our main contribution is a novel variant of the Multistreaming Time-Delay Neural Network (MTDNN) architecture, called MSTRE-Net, which processes the temporal information using multiple streams in parallel with varying resolutions keeping the network more compact, and thus with a faster inference and an improved recognition rate than having identical TDNN streams. In addition, two novel preprocessing steps prior to training the acoustic model are proposed. First, we suggest using recordings from both monoph"},"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":"2108.02625","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-08-05T13:59:11Z","cross_cats_sorted":["cs.CL","cs.IR","eess.AS"],"title_canon_sha256":"0267ba5f6737838e56aca5f25abffc16d26c72bef0ed57a67da6673dd650fabc","abstract_canon_sha256":"d8b3a66f63382602ee744a1ae05899b72a03ae624b209ae397b4198af46a569c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:34.812144Z","signature_b64":"q7pkoFumUH9pJnmjX/uqyvNi02qoKBmu/GywOuN5C9yYeCwl0OFOMdGYkgBKyylU67ogCwTIeTEOBnyIjDcHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5ebfc49eaf9e93a988d1bd537aa21278bd9f94fdbb631ab0fc7b8de909602fc","last_reissued_at":"2026-07-05T03:03:34.811665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:34.811665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSTRE-Net: Multistreaming Acoustic Modeling for Automatic Lyrics Transcription","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR","eess.AS"],"primary_cat":"cs.SD","authors_text":"Emir Demirel, Simon Dixon, Sven Ahlb\\\"ack","submitted_at":"2021-08-05T13:59:11Z","abstract_excerpt":"This paper makes several contributions to automatic lyrics transcription (ALT) research. Our main contribution is a novel variant of the Multistreaming Time-Delay Neural Network (MTDNN) architecture, called MSTRE-Net, which processes the temporal information using multiple streams in parallel with varying resolutions keeping the network more compact, and thus with a faster inference and an improved recognition rate than having identical TDNN streams. In addition, two novel preprocessing steps prior to training the acoustic model are proposed. First, we suggest using recordings from both monoph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02625","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/2108.02625/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":"2108.02625","created_at":"2026-07-05T03:03:34.811727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.02625v1","created_at":"2026-07-05T03:03:34.811727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02625","created_at":"2026-07-05T03:03:34.811727+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXV7YSPK7HUT","created_at":"2026-07-05T03:03:34.811727+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXV7YSPK7HUTVGEN","created_at":"2026-07-05T03:03:34.811727+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXV7YSPK","created_at":"2026-07-05T03:03:34.811727+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/WXV7YSPK7HUTVGENDPKTPKRBE6","json":"https://pith.science/pith/WXV7YSPK7HUTVGENDPKTPKRBE6.json","graph_json":"https://pith.science/api/pith-number/WXV7YSPK7HUTVGENDPKTPKRBE6/graph.json","events_json":"https://pith.science/api/pith-number/WXV7YSPK7HUTVGENDPKTPKRBE6/events.json","paper":"https://pith.science/paper/WXV7YSPK"},"agent_actions":{"view_html":"https://pith.science/pith/WXV7YSPK7HUTVGENDPKTPKRBE6","download_json":"https://pith.science/pith/WXV7YSPK7HUTVGENDPKTPKRBE6.json","view_paper":"https://pith.science/paper/WXV7YSPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.02625&json=true","fetch_graph":"https://pith.science/api/pith-number/WXV7YSPK7HUTVGENDPKTPKRBE6/graph.json","fetch_events":"https://pith.science/api/pith-number/WXV7YSPK7HUTVGENDPKTPKRBE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXV7YSPK7HUTVGENDPKTPKRBE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXV7YSPK7HUTVGENDPKTPKRBE6/action/storage_attestation","attest_author":"https://pith.science/pith/WXV7YSPK7HUTVGENDPKTPKRBE6/action/author_attestation","sign_citation":"https://pith.science/pith/WXV7YSPK7HUTVGENDPKTPKRBE6/action/citation_signature","submit_replication":"https://pith.science/pith/WXV7YSPK7HUTVGENDPKTPKRBE6/action/replication_record"}},"created_at":"2026-07-05T03:03:34.811727+00:00","updated_at":"2026-07-05T03:03:34.811727+00:00"}