{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AR263DC2S3RNVSTYQ5EQMHXJEU","short_pith_number":"pith:AR263DC2","schema_version":"1.0","canonical_sha256":"0475ed8c5a96e2daca788749061ee9252a94d74be47b70dc7de3ddf058915a22","source":{"kind":"arxiv","id":"2407.03495","version":1},"attestation_state":"computed","paper":{"title":"Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Ante Juki\\'c, Boris Ginsburg, Jagadeesh Balam, Kunal Dhawan, Nithin Rao Koluguri, Ryan Langman","submitted_at":"2024-07-03T20:51:41Z","abstract_excerpt":"Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech recognition (ASR), translation, speaker verification, and joint speech-text foundational models. In this work, we present a comprehensive analysis on building ASR systems with discrete codes. We investigate different methods for codec training such as quantization schemes and time-domain vs spectral feature encodings. We further explore ASR training techniques aimed at enhancing performance, training efficiency, and noi"},"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":"2407.03495","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-03T20:51:41Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"0155ff61e51e8c78fdf84e5d2e6f9626356ae28ee4c1c50af0c7f7328a469dbc","abstract_canon_sha256":"ec59d429ef8be66d68e8ec50a4fc0d44165a21b94dd2eb6d65a881b362cbd009"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:27.568480Z","signature_b64":"Y1Kuk4D36ykrMzSn2GQYoSS/DL9egE2zH850Ol7N4IEuZOPGMXhCP1cMjoufMXFWZNZiGrEoGE2npTzOwE4sCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0475ed8c5a96e2daca788749061ee9252a94d74be47b70dc7de3ddf058915a22","last_reissued_at":"2026-07-05T09:11:27.567891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:27.567891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Ante Juki\\'c, Boris Ginsburg, Jagadeesh Balam, Kunal Dhawan, Nithin Rao Koluguri, Ryan Langman","submitted_at":"2024-07-03T20:51:41Z","abstract_excerpt":"Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech recognition (ASR), translation, speaker verification, and joint speech-text foundational models. In this work, we present a comprehensive analysis on building ASR systems with discrete codes. We investigate different methods for codec training such as quantization schemes and time-domain vs spectral feature encodings. We further explore ASR training techniques aimed at enhancing performance, training efficiency, and noi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03495","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/2407.03495/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":"2407.03495","created_at":"2026-07-05T09:11:27.567948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03495v1","created_at":"2026-07-05T09:11:27.567948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03495","created_at":"2026-07-05T09:11:27.567948+00:00"},{"alias_kind":"pith_short_12","alias_value":"AR263DC2S3RN","created_at":"2026-07-05T09:11:27.567948+00:00"},{"alias_kind":"pith_short_16","alias_value":"AR263DC2S3RNVSTY","created_at":"2026-07-05T09:11:27.567948+00:00"},{"alias_kind":"pith_short_8","alias_value":"AR263DC2","created_at":"2026-07-05T09:11:27.567948+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/AR263DC2S3RNVSTYQ5EQMHXJEU","json":"https://pith.science/pith/AR263DC2S3RNVSTYQ5EQMHXJEU.json","graph_json":"https://pith.science/api/pith-number/AR263DC2S3RNVSTYQ5EQMHXJEU/graph.json","events_json":"https://pith.science/api/pith-number/AR263DC2S3RNVSTYQ5EQMHXJEU/events.json","paper":"https://pith.science/paper/AR263DC2"},"agent_actions":{"view_html":"https://pith.science/pith/AR263DC2S3RNVSTYQ5EQMHXJEU","download_json":"https://pith.science/pith/AR263DC2S3RNVSTYQ5EQMHXJEU.json","view_paper":"https://pith.science/paper/AR263DC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03495&json=true","fetch_graph":"https://pith.science/api/pith-number/AR263DC2S3RNVSTYQ5EQMHXJEU/graph.json","fetch_events":"https://pith.science/api/pith-number/AR263DC2S3RNVSTYQ5EQMHXJEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AR263DC2S3RNVSTYQ5EQMHXJEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AR263DC2S3RNVSTYQ5EQMHXJEU/action/storage_attestation","attest_author":"https://pith.science/pith/AR263DC2S3RNVSTYQ5EQMHXJEU/action/author_attestation","sign_citation":"https://pith.science/pith/AR263DC2S3RNVSTYQ5EQMHXJEU/action/citation_signature","submit_replication":"https://pith.science/pith/AR263DC2S3RNVSTYQ5EQMHXJEU/action/replication_record"}},"created_at":"2026-07-05T09:11:27.567948+00:00","updated_at":"2026-07-05T09:11:27.567948+00:00"}