{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4V7R6KWDQGIVKTCMEG4TZK4FZH","short_pith_number":"pith:4V7R6KWD","schema_version":"1.0","canonical_sha256":"e57f1f2ac38191554c4c21b93cab85c9f0dcb04d094f2461b9695e2ab1abd509","source":{"kind":"arxiv","id":"1905.00078","version":2},"attestation_state":"computed","paper":{"title":"Deep Learning for Audio Signal Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"(2) Google, (3) Tampere University, (4) Universit\\'e de Toulon, 5), (5) Austrian Research Institute for Artificial Intelligence), Bo Li (2), Hendrik Purwins (1), Jan Schl\\\"uter (4, Shuo-yiin Chang (2), Tara Sainath (2) ((1) Aalborg University Copenhagen, Tuomas Virtanen (3)","submitted_at":"2019-04-30T19:57:33Z","abstract_excerpt":"Given the recent surge in developments of deep learning, this article provides a review of the state-of-the-art deep learning techniques for audio signal processing. Speech, music, and environmental sound processing are considered side-by-side, in order to point out similarities and differences between the domains, highlighting general methods, problems, key references, and potential for cross-fertilization between areas. The dominant feature representations (in particular, log-mel spectra and raw waveform) and deep learning models are reviewed, including convolutional neural networks, variant"},"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":"1905.00078","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-04-30T19:57:33Z","cross_cats_sorted":["eess.AS","stat.ML"],"title_canon_sha256":"cb959a9198d8ba1dcc2c9e2345cbc403fc1289dfb2710f246c0db28c74aa61eb","abstract_canon_sha256":"214f25da6bd2a5d2df93ed50c12e3b6908cdc260845ab26c8f68cb68920ec692"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:08.923222Z","signature_b64":"0TkU3zy1k3a8WYzyA2FS4u0Z4zwkO1VZ5QBUR+bRX8hjwThPIF8V9+xQsAS4p7dYaKZwLWxf6PWFB/YC7m14CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e57f1f2ac38191554c4c21b93cab85c9f0dcb04d094f2461b9695e2ab1abd509","last_reissued_at":"2026-05-17T23:45:08.922052Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:08.922052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Learning for Audio Signal Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"(2) Google, (3) Tampere University, (4) Universit\\'e de Toulon, 5), (5) Austrian Research Institute for Artificial Intelligence), Bo Li (2), Hendrik Purwins (1), Jan Schl\\\"uter (4, Shuo-yiin Chang (2), Tara Sainath (2) ((1) Aalborg University Copenhagen, Tuomas Virtanen (3)","submitted_at":"2019-04-30T19:57:33Z","abstract_excerpt":"Given the recent surge in developments of deep learning, this article provides a review of the state-of-the-art deep learning techniques for audio signal processing. Speech, music, and environmental sound processing are considered side-by-side, in order to point out similarities and differences between the domains, highlighting general methods, problems, key references, and potential for cross-fertilization between areas. The dominant feature representations (in particular, log-mel spectra and raw waveform) and deep learning models are reviewed, including convolutional neural networks, variant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00078","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":""},"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":"1905.00078","created_at":"2026-05-17T23:45:08.922454+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.00078v2","created_at":"2026-05-17T23:45:08.922454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00078","created_at":"2026-05-17T23:45:08.922454+00:00"},{"alias_kind":"pith_short_12","alias_value":"4V7R6KWDQGIV","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4V7R6KWDQGIVKTCM","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4V7R6KWD","created_at":"2026-05-18T12:33:10.108867+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/4V7R6KWDQGIVKTCMEG4TZK4FZH","json":"https://pith.science/pith/4V7R6KWDQGIVKTCMEG4TZK4FZH.json","graph_json":"https://pith.science/api/pith-number/4V7R6KWDQGIVKTCMEG4TZK4FZH/graph.json","events_json":"https://pith.science/api/pith-number/4V7R6KWDQGIVKTCMEG4TZK4FZH/events.json","paper":"https://pith.science/paper/4V7R6KWD"},"agent_actions":{"view_html":"https://pith.science/pith/4V7R6KWDQGIVKTCMEG4TZK4FZH","download_json":"https://pith.science/pith/4V7R6KWDQGIVKTCMEG4TZK4FZH.json","view_paper":"https://pith.science/paper/4V7R6KWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.00078&json=true","fetch_graph":"https://pith.science/api/pith-number/4V7R6KWDQGIVKTCMEG4TZK4FZH/graph.json","fetch_events":"https://pith.science/api/pith-number/4V7R6KWDQGIVKTCMEG4TZK4FZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4V7R6KWDQGIVKTCMEG4TZK4FZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4V7R6KWDQGIVKTCMEG4TZK4FZH/action/storage_attestation","attest_author":"https://pith.science/pith/4V7R6KWDQGIVKTCMEG4TZK4FZH/action/author_attestation","sign_citation":"https://pith.science/pith/4V7R6KWDQGIVKTCMEG4TZK4FZH/action/citation_signature","submit_replication":"https://pith.science/pith/4V7R6KWDQGIVKTCMEG4TZK4FZH/action/replication_record"}},"created_at":"2026-05-17T23:45:08.922454+00:00","updated_at":"2026-05-17T23:45:08.922454+00:00"}