{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AR263DC2S3RNVSTYQ5EQMHXJEU","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":"ec59d429ef8be66d68e8ec50a4fc0d44165a21b94dd2eb6d65a881b362cbd009","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-03T20:51:41Z","title_canon_sha256":"0155ff61e51e8c78fdf84e5d2e6f9626356ae28ee4c1c50af0c7f7328a469dbc"},"schema_version":"1.0","source":{"id":"2407.03495","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03495","created_at":"2026-07-05T09:11:27Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03495v1","created_at":"2026-07-05T09:11:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03495","created_at":"2026-07-05T09:11:27Z"},{"alias_kind":"pith_short_12","alias_value":"AR263DC2S3RN","created_at":"2026-07-05T09:11:27Z"},{"alias_kind":"pith_short_16","alias_value":"AR263DC2S3RNVSTY","created_at":"2026-07-05T09:11:27Z"},{"alias_kind":"pith_short_8","alias_value":"AR263DC2","created_at":"2026-07-05T09:11:27Z"}],"graph_snapshots":[{"event_id":"sha256:b8edd0d94faeed96944e95f201a4c9b3af1d0aad182eae0bd8b23f180cb6a331","target":"graph","created_at":"2026-07-05T09:11:27Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.03495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ante Juki\\'c, Boris Ginsburg, Jagadeesh Balam, Kunal Dhawan, Nithin Rao Koluguri, Ryan Langman","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-03T20:51:41Z","title":"Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03495","kind":"arxiv","version":1},"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":"sha256:2d2dc23f029475c92b24588f16ffe57e2377cb67e90ea6b37efcb030fff828bd","target":"record","created_at":"2026-07-05T09:11:27Z","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":"ec59d429ef8be66d68e8ec50a4fc0d44165a21b94dd2eb6d65a881b362cbd009","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-03T20:51:41Z","title_canon_sha256":"0155ff61e51e8c78fdf84e5d2e6f9626356ae28ee4c1c50af0c7f7328a469dbc"},"schema_version":"1.0","source":{"id":"2407.03495","kind":"arxiv","version":1}},"canonical_sha256":"0475ed8c5a96e2daca788749061ee9252a94d74be47b70dc7de3ddf058915a22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0475ed8c5a96e2daca788749061ee9252a94d74be47b70dc7de3ddf058915a22","first_computed_at":"2026-07-05T09:11:27.567891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:27.567891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y1Kuk4D36ykrMzSn2GQYoSS/DL9egE2zH850Ol7N4IEuZOPGMXhCP1cMjoufMXFWZNZiGrEoGE2npTzOwE4sCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:27.568480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03495","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d2dc23f029475c92b24588f16ffe57e2377cb67e90ea6b37efcb030fff828bd","sha256:b8edd0d94faeed96944e95f201a4c9b3af1d0aad182eae0bd8b23f180cb6a331"],"state_sha256":"cb300f44e467d5eddf14e570941b7847c52b2a8ac9ec073ac8eecd609609ecf8"}