{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NGGTUPEMMFM5NDHG3ROWJ5QW67","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d1abe70f13ad008bf3cdc5d06c5d0115d0290091f02754181f0de5446467cee4","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-19T08:32:49Z","title_canon_sha256":"4736cad764dd35055b27f672127305baf310956399f22132a8c763e8895be665"},"schema_version":"1.0","source":{"id":"1806.07098","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.07098","created_at":"2026-05-18T00:12:42Z"},{"alias_kind":"arxiv_version","alias_value":"1806.07098v2","created_at":"2026-05-18T00:12:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.07098","created_at":"2026-05-18T00:12:42Z"},{"alias_kind":"pith_short_12","alias_value":"NGGTUPEMMFM5","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NGGTUPEMMFM5NDHG","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NGGTUPEM","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:e6cca34a39a8e42bfcfaeaf82d4e9c905765befa02e409759e0c75b0e8d1d61d","target":"graph","created_at":"2026-05-18T00:12:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Emmanuel Dupoux, Gabriel Synnaeve, Neil Zeghidour, Nicolas Usunier, Ronan Collobert","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-19T08:32:49Z","title":"End-to-End Speech Recognition From the Raw Waveform"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.07098","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b65f4064906156c93b1ca459cdf0b2243946aba83ba44c7605514b608cce8259","target":"record","created_at":"2026-05-18T00:12:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d1abe70f13ad008bf3cdc5d06c5d0115d0290091f02754181f0de5446467cee4","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-19T08:32:49Z","title_canon_sha256":"4736cad764dd35055b27f672127305baf310956399f22132a8c763e8895be665"},"schema_version":"1.0","source":{"id":"1806.07098","kind":"arxiv","version":2}},"canonical_sha256":"698d3a3c8c6159d68ce6dc5d64f616f7d96de74a9cd59a0ad73b7aac3b10857e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"698d3a3c8c6159d68ce6dc5d64f616f7d96de74a9cd59a0ad73b7aac3b10857e","first_computed_at":"2026-05-18T00:12:42.832043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:42.832043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NRGAMadcY5cfEsrgf9wX3dkISztzrrQEmcd9OMazm7JLIz2AG+onP9t0PmESR26ZxlCPtPJW3h/2YXFM4dtCBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:42.832700Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.07098","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b65f4064906156c93b1ca459cdf0b2243946aba83ba44c7605514b608cce8259","sha256:e6cca34a39a8e42bfcfaeaf82d4e9c905765befa02e409759e0c75b0e8d1d61d"],"state_sha256":"b3be40082fb1fd993e15fb3ef632144acaaacf65c7e2aba5161832585e4c8b22"}