{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:72HMZIFXFCV5IQ3TX4GJWVCASQ","short_pith_number":"pith:72HMZIFX","schema_version":"1.0","canonical_sha256":"fe8ecca0b728abd44373bf0c9b5440943920323bf7f693992e587088de96931b","source":{"kind":"arxiv","id":"1805.08501","version":3},"attestation_state":"computed","paper":{"title":"Generative timbre spaces: regularizing variational auto-encoders with perceptual metrics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Adrien Bitton, Axel Chemla--Romeu-Santos, Philippe Esling","submitted_at":"2018-05-22T11:05:46Z","abstract_excerpt":"Timbre spaces have been used in music perception to study the perceptual relationships between instruments based on dissimilarity ratings. However, these spaces do not generalize to novel examples and do not provide an invertible mapping, preventing audio synthesis. In parallel, generative models have aimed to provide methods for synthesizing novel timbres. However, these systems do not provide an understanding of their inner workings and are usually not related to any perceptually relevant information. Here, we show that Variational Auto-Encoders (VAE) can alleviate all of these limitations b"},"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":"1805.08501","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2018-05-22T11:05:46Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"bb06aeff8dec93e010fae8713fa747e597c08c0e6468248c7ce7b0707e1d6a52","abstract_canon_sha256":"3a89c24ca1632c831cc4512f681adcbedd8c2c7107032af3ae82323f6d89dc1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:29.863140Z","signature_b64":"/OZ1IBxpBT3+r7k5UgFizkU9sU5nhiwKEIf6x+R97mmutbopnMCG4GiRdLNgh8L2QmkgIRPbUn7TB47yJXPIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe8ecca0b728abd44373bf0c9b5440943920323bf7f693992e587088de96931b","last_reissued_at":"2026-05-18T00:04:29.862691Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:29.862691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative timbre spaces: regularizing variational auto-encoders with perceptual metrics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Adrien Bitton, Axel Chemla--Romeu-Santos, Philippe Esling","submitted_at":"2018-05-22T11:05:46Z","abstract_excerpt":"Timbre spaces have been used in music perception to study the perceptual relationships between instruments based on dissimilarity ratings. However, these spaces do not generalize to novel examples and do not provide an invertible mapping, preventing audio synthesis. In parallel, generative models have aimed to provide methods for synthesizing novel timbres. However, these systems do not provide an understanding of their inner workings and are usually not related to any perceptually relevant information. Here, we show that Variational Auto-Encoders (VAE) can alleviate all of these limitations b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08501","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1805.08501","created_at":"2026-05-18T00:04:29.862761+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08501v3","created_at":"2026-05-18T00:04:29.862761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08501","created_at":"2026-05-18T00:04:29.862761+00:00"},{"alias_kind":"pith_short_12","alias_value":"72HMZIFXFCV5","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"72HMZIFXFCV5IQ3T","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"72HMZIFX","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.09972","citing_title":"Classical Music Prediction and Composition by means of Variational Autoencoders","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00971","citing_title":"Universal audio synthesizer control with normalizing flows","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/72HMZIFXFCV5IQ3TX4GJWVCASQ","json":"https://pith.science/pith/72HMZIFXFCV5IQ3TX4GJWVCASQ.json","graph_json":"https://pith.science/api/pith-number/72HMZIFXFCV5IQ3TX4GJWVCASQ/graph.json","events_json":"https://pith.science/api/pith-number/72HMZIFXFCV5IQ3TX4GJWVCASQ/events.json","paper":"https://pith.science/paper/72HMZIFX"},"agent_actions":{"view_html":"https://pith.science/pith/72HMZIFXFCV5IQ3TX4GJWVCASQ","download_json":"https://pith.science/pith/72HMZIFXFCV5IQ3TX4GJWVCASQ.json","view_paper":"https://pith.science/paper/72HMZIFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08501&json=true","fetch_graph":"https://pith.science/api/pith-number/72HMZIFXFCV5IQ3TX4GJWVCASQ/graph.json","fetch_events":"https://pith.science/api/pith-number/72HMZIFXFCV5IQ3TX4GJWVCASQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72HMZIFXFCV5IQ3TX4GJWVCASQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72HMZIFXFCV5IQ3TX4GJWVCASQ/action/storage_attestation","attest_author":"https://pith.science/pith/72HMZIFXFCV5IQ3TX4GJWVCASQ/action/author_attestation","sign_citation":"https://pith.science/pith/72HMZIFXFCV5IQ3TX4GJWVCASQ/action/citation_signature","submit_replication":"https://pith.science/pith/72HMZIFXFCV5IQ3TX4GJWVCASQ/action/replication_record"}},"created_at":"2026-05-18T00:04:29.862761+00:00","updated_at":"2026-05-18T00:04:29.862761+00:00"}