{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UO644SXM7JYIAZQ5AUUNLLAM7S","short_pith_number":"pith:UO644SXM","schema_version":"1.0","canonical_sha256":"a3bdce4aecfa7080661d0528d5ac0cfcb5c3de5a477284b824a4d4ee8f67d83e","source":{"kind":"arxiv","id":"2001.09989","version":2},"attestation_state":"computed","paper":{"title":"The impact of Audio input representations on neural network based music transcription","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dorien Herremans, Kat Agres, Kin Wai Cheuk","submitted_at":"2020-01-25T03:47:21Z","abstract_excerpt":"This paper thoroughly analyses the effect of different input representations on polyphonic multi-instrument music transcription. We use our own GPU based spectrogram extraction tool, nnAudio, to investigate the influence of using a linear-frequency spectrogram, log-frequency spectrogram, Mel spectrogram, and constant-Q transform (CQT). Our results show that a $8.33$% increase in transcription accuracy and a $9.39$% reduction in error can be obtained by choosing the appropriate input representation (log-frequency spectrogram with STFT window length 4,096 and 2,048 frequency bins in the spectrog"},"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":"2001.09989","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-01-25T03:47:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1b33debe7b0c9ffcfe4c8aac5ccbf8d887b619151e700ddaf6e00bb2079fce1f","abstract_canon_sha256":"2d0eba4687a668a619791b3a034ba85c2d0335434891b0f7e1c3ee4b6674832f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:20:52.579170Z","signature_b64":"LxzoP6j92bnOrRomJRf2KQUT4PfnQaRty+Rrf9UdqNip0K/8XgDBJT1MilkqRT6kW8T8fC8UXCOyIJqulFKEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3bdce4aecfa7080661d0528d5ac0cfcb5c3de5a477284b824a4d4ee8f67d83e","last_reissued_at":"2026-07-05T01:20:52.578646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:20:52.578646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The impact of Audio input representations on neural network based music transcription","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dorien Herremans, Kat Agres, Kin Wai Cheuk","submitted_at":"2020-01-25T03:47:21Z","abstract_excerpt":"This paper thoroughly analyses the effect of different input representations on polyphonic multi-instrument music transcription. We use our own GPU based spectrogram extraction tool, nnAudio, to investigate the influence of using a linear-frequency spectrogram, log-frequency spectrogram, Mel spectrogram, and constant-Q transform (CQT). Our results show that a $8.33$% increase in transcription accuracy and a $9.39$% reduction in error can be obtained by choosing the appropriate input representation (log-frequency spectrogram with STFT window length 4,096 and 2,048 frequency bins in the spectrog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.09989","kind":"arxiv","version":2},"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/2001.09989/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":"2001.09989","created_at":"2026-07-05T01:20:52.578712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.09989v2","created_at":"2026-07-05T01:20:52.578712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.09989","created_at":"2026-07-05T01:20:52.578712+00:00"},{"alias_kind":"pith_short_12","alias_value":"UO644SXM7JYI","created_at":"2026-07-05T01:20:52.578712+00:00"},{"alias_kind":"pith_short_16","alias_value":"UO644SXM7JYIAZQ5","created_at":"2026-07-05T01:20:52.578712+00:00"},{"alias_kind":"pith_short_8","alias_value":"UO644SXM","created_at":"2026-07-05T01:20:52.578712+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/UO644SXM7JYIAZQ5AUUNLLAM7S","json":"https://pith.science/pith/UO644SXM7JYIAZQ5AUUNLLAM7S.json","graph_json":"https://pith.science/api/pith-number/UO644SXM7JYIAZQ5AUUNLLAM7S/graph.json","events_json":"https://pith.science/api/pith-number/UO644SXM7JYIAZQ5AUUNLLAM7S/events.json","paper":"https://pith.science/paper/UO644SXM"},"agent_actions":{"view_html":"https://pith.science/pith/UO644SXM7JYIAZQ5AUUNLLAM7S","download_json":"https://pith.science/pith/UO644SXM7JYIAZQ5AUUNLLAM7S.json","view_paper":"https://pith.science/paper/UO644SXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.09989&json=true","fetch_graph":"https://pith.science/api/pith-number/UO644SXM7JYIAZQ5AUUNLLAM7S/graph.json","fetch_events":"https://pith.science/api/pith-number/UO644SXM7JYIAZQ5AUUNLLAM7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UO644SXM7JYIAZQ5AUUNLLAM7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UO644SXM7JYIAZQ5AUUNLLAM7S/action/storage_attestation","attest_author":"https://pith.science/pith/UO644SXM7JYIAZQ5AUUNLLAM7S/action/author_attestation","sign_citation":"https://pith.science/pith/UO644SXM7JYIAZQ5AUUNLLAM7S/action/citation_signature","submit_replication":"https://pith.science/pith/UO644SXM7JYIAZQ5AUUNLLAM7S/action/replication_record"}},"created_at":"2026-07-05T01:20:52.578712+00:00","updated_at":"2026-07-05T01:20:52.578712+00:00"}