{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NGGTUPEMMFM5NDHG3ROWJ5QW67","short_pith_number":"pith:NGGTUPEM","schema_version":"1.0","canonical_sha256":"698d3a3c8c6159d68ce6dc5d64f616f7d96de74a9cd59a0ad73b7aac3b10857e","source":{"kind":"arxiv","id":"1806.07098","version":2},"attestation_state":"computed","paper":{"title":"End-to-End Speech Recognition From the Raw Waveform","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Emmanuel Dupoux, Gabriel Synnaeve, Neil Zeghidour, Nicolas Usunier, Ronan Collobert","submitted_at":"2018-06-19T08:32:49Z","abstract_excerpt":"State-of-the-art speech recognition systems rely on fixed, hand-crafted features such as mel-filterbanks to preprocess the waveform before the training pipeline. In this paper, we study end-to-end systems trained directly from the raw waveform, building on two alternatives for trainable replacements of mel-filterbanks that use a convolutional architecture. The first one is inspired by gammatone filterbanks (Hoshen et al., 2015; Sainath et al, 2015), and the second one by the scattering transform (Zeghidour et al., 2017). We propose two modifications to these architectures and systematically co"},"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":"1806.07098","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-19T08:32:49Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4736cad764dd35055b27f672127305baf310956399f22132a8c763e8895be665","abstract_canon_sha256":"d1abe70f13ad008bf3cdc5d06c5d0115d0290091f02754181f0de5446467cee4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:42.832700Z","signature_b64":"NRGAMadcY5cfEsrgf9wX3dkISztzrrQEmcd9OMazm7JLIz2AG+onP9t0PmESR26ZxlCPtPJW3h/2YXFM4dtCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"698d3a3c8c6159d68ce6dc5d64f616f7d96de74a9cd59a0ad73b7aac3b10857e","last_reissued_at":"2026-05-18T00:12:42.832043Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:42.832043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Speech Recognition From the Raw Waveform","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Emmanuel Dupoux, Gabriel Synnaeve, Neil Zeghidour, Nicolas Usunier, Ronan Collobert","submitted_at":"2018-06-19T08:32:49Z","abstract_excerpt":"State-of-the-art speech recognition systems rely on fixed, hand-crafted features such as mel-filterbanks to preprocess the waveform before the training pipeline. In this paper, we study end-to-end systems trained directly from the raw waveform, building on two alternatives for trainable replacements of mel-filterbanks that use a convolutional architecture. The first one is inspired by gammatone filterbanks (Hoshen et al., 2015; Sainath et al, 2015), and the second one by the scattering transform (Zeghidour et al., 2017). We propose two modifications to these architectures and systematically co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.07098","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":"1806.07098","created_at":"2026-05-18T00:12:42.832147+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.07098v2","created_at":"2026-05-18T00:12:42.832147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.07098","created_at":"2026-05-18T00:12:42.832147+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGGTUPEMMFM5","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGGTUPEMMFM5NDHG","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGGTUPEM","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09426","citing_title":"End-to-End ASR for Code-switched Hindi-English Speech","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NGGTUPEMMFM5NDHG3ROWJ5QW67","json":"https://pith.science/pith/NGGTUPEMMFM5NDHG3ROWJ5QW67.json","graph_json":"https://pith.science/api/pith-number/NGGTUPEMMFM5NDHG3ROWJ5QW67/graph.json","events_json":"https://pith.science/api/pith-number/NGGTUPEMMFM5NDHG3ROWJ5QW67/events.json","paper":"https://pith.science/paper/NGGTUPEM"},"agent_actions":{"view_html":"https://pith.science/pith/NGGTUPEMMFM5NDHG3ROWJ5QW67","download_json":"https://pith.science/pith/NGGTUPEMMFM5NDHG3ROWJ5QW67.json","view_paper":"https://pith.science/paper/NGGTUPEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.07098&json=true","fetch_graph":"https://pith.science/api/pith-number/NGGTUPEMMFM5NDHG3ROWJ5QW67/graph.json","fetch_events":"https://pith.science/api/pith-number/NGGTUPEMMFM5NDHG3ROWJ5QW67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGGTUPEMMFM5NDHG3ROWJ5QW67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGGTUPEMMFM5NDHG3ROWJ5QW67/action/storage_attestation","attest_author":"https://pith.science/pith/NGGTUPEMMFM5NDHG3ROWJ5QW67/action/author_attestation","sign_citation":"https://pith.science/pith/NGGTUPEMMFM5NDHG3ROWJ5QW67/action/citation_signature","submit_replication":"https://pith.science/pith/NGGTUPEMMFM5NDHG3ROWJ5QW67/action/replication_record"}},"created_at":"2026-05-18T00:12:42.832147+00:00","updated_at":"2026-05-18T00:12:42.832147+00:00"}