{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FZU5HAJQ52MO4UIVB5VYBL7D7W","short_pith_number":"pith:FZU5HAJQ","schema_version":"1.0","canonical_sha256":"2e69d38130ee98ee51150f6b80afe3fd87d009de2b5f506e8a1a90f1d5443e79","source":{"kind":"arxiv","id":"2107.10708","version":1},"attestation_state":"computed","paper":{"title":"CarneliNet: Neural Mixture Model for Automatic Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Aleksei Kalinov, Boris Ginsburg, Jagadeesh Balam, Somshubra Majumdar","submitted_at":"2021-07-22T14:29:21Z","abstract_excerpt":"End-to-end automatic speech recognition systems have achieved great accuracy by using deeper and deeper models. However, the increased depth comes with a larger receptive field that can negatively impact model performance in streaming scenarios. We propose an alternative approach that we call Neural Mixture Model. The basic idea is to introduce a parallel mixture of shallow networks instead of a very deep network. To validate this idea we design CarneliNet -- a CTC-based neural network composed of three mega-blocks. Each mega-block consists of multiple parallel shallow sub-networks based on 1D"},"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":"2107.10708","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-07-22T14:29:21Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"c76e08e41f0f6bb8211e0a5583ec4d49aab6177824a6f058235635ed993d2b46","abstract_canon_sha256":"273af324fabde3d3caba40b85e60982168317b255d4b7cd09b85c472c9561563"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:02.898830Z","signature_b64":"UvJCouUQlBsues9nQp9sMKxq2WR9w6q14/N2MHUUwKiiVArZLMVxwAlvusq0XVYa2wKDSFX4fEmP0tdedxIlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e69d38130ee98ee51150f6b80afe3fd87d009de2b5f506e8a1a90f1d5443e79","last_reissued_at":"2026-07-05T03:00:02.898399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:02.898399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CarneliNet: Neural Mixture Model for Automatic Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Aleksei Kalinov, Boris Ginsburg, Jagadeesh Balam, Somshubra Majumdar","submitted_at":"2021-07-22T14:29:21Z","abstract_excerpt":"End-to-end automatic speech recognition systems have achieved great accuracy by using deeper and deeper models. However, the increased depth comes with a larger receptive field that can negatively impact model performance in streaming scenarios. We propose an alternative approach that we call Neural Mixture Model. The basic idea is to introduce a parallel mixture of shallow networks instead of a very deep network. To validate this idea we design CarneliNet -- a CTC-based neural network composed of three mega-blocks. Each mega-block consists of multiple parallel shallow sub-networks based on 1D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.10708","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/2107.10708/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":"2107.10708","created_at":"2026-07-05T03:00:02.898465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.10708v1","created_at":"2026-07-05T03:00:02.898465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.10708","created_at":"2026-07-05T03:00:02.898465+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZU5HAJQ52MO","created_at":"2026-07-05T03:00:02.898465+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZU5HAJQ52MO4UIV","created_at":"2026-07-05T03:00:02.898465+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZU5HAJQ","created_at":"2026-07-05T03:00:02.898465+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/FZU5HAJQ52MO4UIVB5VYBL7D7W","json":"https://pith.science/pith/FZU5HAJQ52MO4UIVB5VYBL7D7W.json","graph_json":"https://pith.science/api/pith-number/FZU5HAJQ52MO4UIVB5VYBL7D7W/graph.json","events_json":"https://pith.science/api/pith-number/FZU5HAJQ52MO4UIVB5VYBL7D7W/events.json","paper":"https://pith.science/paper/FZU5HAJQ"},"agent_actions":{"view_html":"https://pith.science/pith/FZU5HAJQ52MO4UIVB5VYBL7D7W","download_json":"https://pith.science/pith/FZU5HAJQ52MO4UIVB5VYBL7D7W.json","view_paper":"https://pith.science/paper/FZU5HAJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.10708&json=true","fetch_graph":"https://pith.science/api/pith-number/FZU5HAJQ52MO4UIVB5VYBL7D7W/graph.json","fetch_events":"https://pith.science/api/pith-number/FZU5HAJQ52MO4UIVB5VYBL7D7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZU5HAJQ52MO4UIVB5VYBL7D7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZU5HAJQ52MO4UIVB5VYBL7D7W/action/storage_attestation","attest_author":"https://pith.science/pith/FZU5HAJQ52MO4UIVB5VYBL7D7W/action/author_attestation","sign_citation":"https://pith.science/pith/FZU5HAJQ52MO4UIVB5VYBL7D7W/action/citation_signature","submit_replication":"https://pith.science/pith/FZU5HAJQ52MO4UIVB5VYBL7D7W/action/replication_record"}},"created_at":"2026-07-05T03:00:02.898465+00:00","updated_at":"2026-07-05T03:00:02.898465+00:00"}