{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:345VMX6L2JKSFRMD7FTUDBSLWA","short_pith_number":"pith:345VMX6L","schema_version":"1.0","canonical_sha256":"df3b565fcbd25522c583f96741864bb023ab47ff386bc8edc170a42d49a3a94c","source":{"kind":"arxiv","id":"2409.05377","version":1},"attestation_state":"computed","paper":{"title":"BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Detai Xin, Hiroshi Saruwatari, Shinnosuke Takamichi, Xu Tan","submitted_at":"2024-09-09T07:18:07Z","abstract_excerpt":"We present BigCodec, a low-bitrate neural speech codec. While recent neural speech codecs have shown impressive progress, their performance significantly deteriorates at low bitrates (around 1 kbps). Although a low bitrate inherently restricts performance, other factors, such as model capacity, also hinder further improvements. To address this problem, we scale up the model size to 159M parameters that is more than 10 times larger than popular codecs with about 10M parameters. Besides, we integrate sequential models into traditional convolutional architectures to better capture temporal depend"},"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":"2409.05377","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-09T07:18:07Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"a20a24e07325252c561ea0f6448d6262349c3863da33399ea61eec62ff1eb583","abstract_canon_sha256":"1f1d1ddd94c04e489cc32fe78a24563458adc8d423e828334991d20f34f431d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:48.439169Z","signature_b64":"tmil/7EWVl9pQKm6Q5yyQcLH7ANtwgVDPwyRuX4AjKvBwag5ltlgGgPZbCIMhnrZ57z29+b3xQfN//JsijOJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df3b565fcbd25522c583f96741864bb023ab47ff386bc8edc170a42d49a3a94c","last_reissued_at":"2026-07-05T09:04:48.438767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:48.438767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Detai Xin, Hiroshi Saruwatari, Shinnosuke Takamichi, Xu Tan","submitted_at":"2024-09-09T07:18:07Z","abstract_excerpt":"We present BigCodec, a low-bitrate neural speech codec. While recent neural speech codecs have shown impressive progress, their performance significantly deteriorates at low bitrates (around 1 kbps). Although a low bitrate inherently restricts performance, other factors, such as model capacity, also hinder further improvements. To address this problem, we scale up the model size to 159M parameters that is more than 10 times larger than popular codecs with about 10M parameters. Besides, we integrate sequential models into traditional convolutional architectures to better capture temporal depend"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05377","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/2409.05377/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":"2409.05377","created_at":"2026-07-05T09:04:48.438819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.05377v1","created_at":"2026-07-05T09:04:48.438819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05377","created_at":"2026-07-05T09:04:48.438819+00:00"},{"alias_kind":"pith_short_12","alias_value":"345VMX6L2JKS","created_at":"2026-07-05T09:04:48.438819+00:00"},{"alias_kind":"pith_short_16","alias_value":"345VMX6L2JKSFRMD","created_at":"2026-07-05T09:04:48.438819+00:00"},{"alias_kind":"pith_short_8","alias_value":"345VMX6L","created_at":"2026-07-05T09:04:48.438819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21157","citing_title":"SDP-Codec: A Speaker-Decoupled Speech Codec with Pitch Injection for Low-Bitrate Coding and Zero-Shot Voice Conversion","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12940","citing_title":"Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11611","citing_title":"SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11631","citing_title":"Benchmarking Neural Speech Compression from a Rate-Distortion Perspective","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05892","citing_title":"VoCodec: A Low-bitrate Streamable Neural Speech Codec with Voicing-driven Quantization","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05876","citing_title":"An Ultra-Low-Bitrate Neural Speech Codec with Plain-to-Pseudo Synergistic Vector Quantization","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26812","citing_title":"CFMDCTCodec: A Low-Bitrate Neural Speech Codec with Noise-Prior-aware Conditional Flow Matching for MDCT-Spectral Enhancement","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":210,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29480","citing_title":"DTM-Codec: Dynamic Token Masking for VFR Speech Coding with Efficient Boundary Selection","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25669","citing_title":"Ultra-Low-Bitrate Mel-Spectrogram-based Neural Speech Coding with Flow-Matching-based Refinement and Vocoding-driven Reconstruction","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27627","citing_title":"HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01537","citing_title":"Two-Dimensional Quantization for Geometry-Aware Audio Coding","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19541","citing_title":"Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2512.20211","citing_title":"Aliasing-Free Neural Audio Synthesis","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11192","citing_title":"Exploring Token-Space Manipulation in Latent Audio Tokenizers","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11098","citing_title":"AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26296","citing_title":"SPG-Codec: Exploring the Role and Boundaries of Semantic Priors in Ultra-Low-Bitrate Neural Speech Coding","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08608","citing_title":"Reducing Linguistic Hallucination in LM-Based Speech Enhancement via Noise-Invariant Acoustic-Semantic Distillation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17852","citing_title":"LLM-Codec: Neural Audio Codec Meets Language Model Objectives","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/345VMX6L2JKSFRMD7FTUDBSLWA","json":"https://pith.science/pith/345VMX6L2JKSFRMD7FTUDBSLWA.json","graph_json":"https://pith.science/api/pith-number/345VMX6L2JKSFRMD7FTUDBSLWA/graph.json","events_json":"https://pith.science/api/pith-number/345VMX6L2JKSFRMD7FTUDBSLWA/events.json","paper":"https://pith.science/paper/345VMX6L"},"agent_actions":{"view_html":"https://pith.science/pith/345VMX6L2JKSFRMD7FTUDBSLWA","download_json":"https://pith.science/pith/345VMX6L2JKSFRMD7FTUDBSLWA.json","view_paper":"https://pith.science/paper/345VMX6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.05377&json=true","fetch_graph":"https://pith.science/api/pith-number/345VMX6L2JKSFRMD7FTUDBSLWA/graph.json","fetch_events":"https://pith.science/api/pith-number/345VMX6L2JKSFRMD7FTUDBSLWA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/345VMX6L2JKSFRMD7FTUDBSLWA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/345VMX6L2JKSFRMD7FTUDBSLWA/action/storage_attestation","attest_author":"https://pith.science/pith/345VMX6L2JKSFRMD7FTUDBSLWA/action/author_attestation","sign_citation":"https://pith.science/pith/345VMX6L2JKSFRMD7FTUDBSLWA/action/citation_signature","submit_replication":"https://pith.science/pith/345VMX6L2JKSFRMD7FTUDBSLWA/action/replication_record"}},"created_at":"2026-07-05T09:04:48.438819+00:00","updated_at":"2026-07-05T09:04:48.438819+00:00"}