{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:25DWCHCANA7S734TQQMKSQAPRL","short_pith_number":"pith:25DWCHCA","schema_version":"1.0","canonical_sha256":"d747611c40683f2fef938418a9400f8af6bdd7f2543d7cd29f90b222c00f7611","source":{"kind":"arxiv","id":"1711.01161","version":2},"attestation_state":"computed","paper":{"title":"Learning Filterbanks from Raw Speech for Phone Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Emmanuel Dupoux, Gabriel Synnaeve, Iasonas Kokkinos, Neil Zeghidour, Nicolas Usunier, Thomas Schatz","submitted_at":"2017-11-03T13:56:53Z","abstract_excerpt":"We train a bank of complex filters that operates on the raw waveform and is fed into a convolutional neural network for end-to-end phone recognition. These time-domain filterbanks (TD-filterbanks) are initialized as an approximation of mel-filterbanks, and then fine-tuned jointly with the remaining convolutional architecture. We perform phone recognition experiments on TIMIT and show that for several architectures, models trained on TD-filterbanks consistently outperform their counterparts trained on comparable mel-filterbanks. We get our best performance by learning all front-end steps, from "},"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":"1711.01161","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-03T13:56:53Z","cross_cats_sorted":[],"title_canon_sha256":"698230ade9a0bac550b3408bd09414387f665c2270106afac32e5ed61f5eb03d","abstract_canon_sha256":"eb228273ab1f7d4418197fad2161b57ce5b73ab934a581e4eed8dfd680cc4552"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:16.882136Z","signature_b64":"SC/SySbuRKMDFDhT0FOdQ2uFopSExSSJNMwjaay7dbD5//BsajF77ZaLqnRiL3wNHSOLGdgGHWhEambKpfWZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d747611c40683f2fef938418a9400f8af6bdd7f2543d7cd29f90b222c00f7611","last_reissued_at":"2026-05-18T00:19:16.881524Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:16.881524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Filterbanks from Raw Speech for Phone Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Emmanuel Dupoux, Gabriel Synnaeve, Iasonas Kokkinos, Neil Zeghidour, Nicolas Usunier, Thomas Schatz","submitted_at":"2017-11-03T13:56:53Z","abstract_excerpt":"We train a bank of complex filters that operates on the raw waveform and is fed into a convolutional neural network for end-to-end phone recognition. These time-domain filterbanks (TD-filterbanks) are initialized as an approximation of mel-filterbanks, and then fine-tuned jointly with the remaining convolutional architecture. We perform phone recognition experiments on TIMIT and show that for several architectures, models trained on TD-filterbanks consistently outperform their counterparts trained on comparable mel-filterbanks. We get our best performance by learning all front-end steps, from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.01161","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":"1711.01161","created_at":"2026-05-18T00:19:16.881646+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.01161v2","created_at":"2026-05-18T00:19:16.881646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.01161","created_at":"2026-05-18T00:19:16.881646+00:00"},{"alias_kind":"pith_short_12","alias_value":"25DWCHCANA7S","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"25DWCHCANA7S734T","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"25DWCHCA","created_at":"2026-05-18T12:30:55.937587+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/25DWCHCANA7S734TQQMKSQAPRL","json":"https://pith.science/pith/25DWCHCANA7S734TQQMKSQAPRL.json","graph_json":"https://pith.science/api/pith-number/25DWCHCANA7S734TQQMKSQAPRL/graph.json","events_json":"https://pith.science/api/pith-number/25DWCHCANA7S734TQQMKSQAPRL/events.json","paper":"https://pith.science/paper/25DWCHCA"},"agent_actions":{"view_html":"https://pith.science/pith/25DWCHCANA7S734TQQMKSQAPRL","download_json":"https://pith.science/pith/25DWCHCANA7S734TQQMKSQAPRL.json","view_paper":"https://pith.science/paper/25DWCHCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.01161&json=true","fetch_graph":"https://pith.science/api/pith-number/25DWCHCANA7S734TQQMKSQAPRL/graph.json","fetch_events":"https://pith.science/api/pith-number/25DWCHCANA7S734TQQMKSQAPRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25DWCHCANA7S734TQQMKSQAPRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25DWCHCANA7S734TQQMKSQAPRL/action/storage_attestation","attest_author":"https://pith.science/pith/25DWCHCANA7S734TQQMKSQAPRL/action/author_attestation","sign_citation":"https://pith.science/pith/25DWCHCANA7S734TQQMKSQAPRL/action/citation_signature","submit_replication":"https://pith.science/pith/25DWCHCANA7S734TQQMKSQAPRL/action/replication_record"}},"created_at":"2026-05-18T00:19:16.881646+00:00","updated_at":"2026-05-18T00:19:16.881646+00:00"}