{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AVDAFAA5KYMWWFCXI5IH4MEVWP","short_pith_number":"pith:AVDAFAA5","schema_version":"1.0","canonical_sha256":"054602801d56196b145747507e3095b3f5267478d3b03caceac54c10783cec42","source":{"kind":"arxiv","id":"2505.23509","version":1},"attestation_state":"computed","paper":{"title":"Spectrotemporal Modulation: Efficient and Interpretable Feature Representation for Classifying Speech, Music, and Environmental Sounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andrew Chang, David Poeppel, Iran R. Roman, Yike Li","submitted_at":"2025-05-29T14:52:47Z","abstract_excerpt":"Audio DNNs have demonstrated impressive performance on various machine listening tasks; however, most of their representations are computationally costly and uninterpretable, leaving room for optimization. Here, we propose a novel approach centered on spectrotemporal modulation (STM) features, a signal processing method that mimics the neurophysiological representation in the human auditory cortex. The classification performance of our STM-based model, without any pretraining, is comparable to that of pretrained audio DNNs across diverse naturalistic speech, music, and environmental sounds, wh"},"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":"2505.23509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-29T14:52:47Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"6cc5cdc49990d21549c3f28e99f01fca043270449eca2f8c5727170fc0bc855c","abstract_canon_sha256":"740e0e228002709e49396f291646c2f4704fd6172a0945a1d8e006a135d06736"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:40.414490Z","signature_b64":"OcLKtAeGqnWYP/rG15LzK3U0cVMq1I1NXWjxzDwUIUIEIDd7xQo6Id2jO8hgCMGkJqugbeO2zaTY0D4McZJlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"054602801d56196b145747507e3095b3f5267478d3b03caceac54c10783cec42","last_reissued_at":"2026-07-05T11:55:40.414000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:40.414000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectrotemporal Modulation: Efficient and Interpretable Feature Representation for Classifying Speech, Music, and Environmental Sounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andrew Chang, David Poeppel, Iran R. Roman, Yike Li","submitted_at":"2025-05-29T14:52:47Z","abstract_excerpt":"Audio DNNs have demonstrated impressive performance on various machine listening tasks; however, most of their representations are computationally costly and uninterpretable, leaving room for optimization. Here, we propose a novel approach centered on spectrotemporal modulation (STM) features, a signal processing method that mimics the neurophysiological representation in the human auditory cortex. The classification performance of our STM-based model, without any pretraining, is comparable to that of pretrained audio DNNs across diverse naturalistic speech, music, and environmental sounds, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23509","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/2505.23509/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":"2505.23509","created_at":"2026-07-05T11:55:40.414052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23509v1","created_at":"2026-07-05T11:55:40.414052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23509","created_at":"2026-07-05T11:55:40.414052+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVDAFAA5KYMW","created_at":"2026-07-05T11:55:40.414052+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVDAFAA5KYMWWFCX","created_at":"2026-07-05T11:55:40.414052+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVDAFAA5","created_at":"2026-07-05T11:55:40.414052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23509","citing_title":"Spectrotemporal Modulation: Efficient and Interpretable Feature Representation for Classifying Speech, Music, and Environmental Sounds","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AVDAFAA5KYMWWFCXI5IH4MEVWP","json":"https://pith.science/pith/AVDAFAA5KYMWWFCXI5IH4MEVWP.json","graph_json":"https://pith.science/api/pith-number/AVDAFAA5KYMWWFCXI5IH4MEVWP/graph.json","events_json":"https://pith.science/api/pith-number/AVDAFAA5KYMWWFCXI5IH4MEVWP/events.json","paper":"https://pith.science/paper/AVDAFAA5"},"agent_actions":{"view_html":"https://pith.science/pith/AVDAFAA5KYMWWFCXI5IH4MEVWP","download_json":"https://pith.science/pith/AVDAFAA5KYMWWFCXI5IH4MEVWP.json","view_paper":"https://pith.science/paper/AVDAFAA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23509&json=true","fetch_graph":"https://pith.science/api/pith-number/AVDAFAA5KYMWWFCXI5IH4MEVWP/graph.json","fetch_events":"https://pith.science/api/pith-number/AVDAFAA5KYMWWFCXI5IH4MEVWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVDAFAA5KYMWWFCXI5IH4MEVWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVDAFAA5KYMWWFCXI5IH4MEVWP/action/storage_attestation","attest_author":"https://pith.science/pith/AVDAFAA5KYMWWFCXI5IH4MEVWP/action/author_attestation","sign_citation":"https://pith.science/pith/AVDAFAA5KYMWWFCXI5IH4MEVWP/action/citation_signature","submit_replication":"https://pith.science/pith/AVDAFAA5KYMWWFCXI5IH4MEVWP/action/replication_record"}},"created_at":"2026-07-05T11:55:40.414052+00:00","updated_at":"2026-07-05T11:55:40.414052+00:00"}