{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O26T7HA6TRDJC5QNIPHWIBMSYP","short_pith_number":"pith:O26T7HA6","schema_version":"1.0","canonical_sha256":"76bd3f9c1e9c4691760d43cf640592c3d6829cf8c7aec08dfe02e024c9b59bb4","source":{"kind":"arxiv","id":"2408.16532","version":3},"attestation_state":"computed","paper":{"title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Jialong Zuo, Minghui Fang, Qian Chen, Qian Yang, Rongjie Huang, Ruiqi Li, Shengpeng Ji, Siqi Zheng, Wen Wang, Xiaoda Yang, Xize Cheng, Yidi Jiang, Yifu Chen, Zehan Wang, Zhou Zhao, Ziang Zhang, Ziyue Jiang","submitted_at":"2024-08-29T13:43:36Z","abstract_excerpt":"Language models have been effectively applied to modeling natural signals, such as images, video, speech, and audio. A crucial component of these models is the codec tokenizer, which compresses high-dimensional natural signals into lower-dimensional discrete tokens. In this paper, we introduce WavTokenizer, which offers several advantages over previous SOTA acoustic codec models in the audio domain: 1)extreme compression. By compressing the layers of quantizers and the temporal dimension of the discrete codec, one-second audio of 24kHz sampling rate requires only a single quantizer with 40 or "},"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":"2408.16532","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-29T13:43:36Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.SP"],"title_canon_sha256":"510606605a7037abf2f72af3e2aae5e1b26edbe8723cdab2b958d5a37bfcfb40","abstract_canon_sha256":"f81039488d194d612e5411ff3c6a70c60c79a73d8afdc5ebfee152d539c2a992"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:27.569644Z","signature_b64":"pohf2Ao8fQkh5knwjnCJZXKCAvF20X3kAE63ZmEBul5otCuqBYsX7k3nXneojNmZvnHb59E2Ip7OgpIB+B2DDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76bd3f9c1e9c4691760d43cf640592c3d6829cf8c7aec08dfe02e024c9b59bb4","last_reissued_at":"2026-07-05T10:19:27.569231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:27.569231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Jialong Zuo, Minghui Fang, Qian Chen, Qian Yang, Rongjie Huang, Ruiqi Li, Shengpeng Ji, Siqi Zheng, Wen Wang, Xiaoda Yang, Xize Cheng, Yidi Jiang, Yifu Chen, Zehan Wang, Zhou Zhao, Ziang Zhang, Ziyue Jiang","submitted_at":"2024-08-29T13:43:36Z","abstract_excerpt":"Language models have been effectively applied to modeling natural signals, such as images, video, speech, and audio. A crucial component of these models is the codec tokenizer, which compresses high-dimensional natural signals into lower-dimensional discrete tokens. In this paper, we introduce WavTokenizer, which offers several advantages over previous SOTA acoustic codec models in the audio domain: 1)extreme compression. By compressing the layers of quantizers and the temporal dimension of the discrete codec, one-second audio of 24kHz sampling rate requires only a single quantizer with 40 or "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16532","kind":"arxiv","version":3},"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/2408.16532/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":"2408.16532","created_at":"2026-07-05T10:19:27.569288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.16532v3","created_at":"2026-07-05T10:19:27.569288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16532","created_at":"2026-07-05T10:19:27.569288+00:00"},{"alias_kind":"pith_short_12","alias_value":"O26T7HA6TRDJ","created_at":"2026-07-05T10:19:27.569288+00:00"},{"alias_kind":"pith_short_16","alias_value":"O26T7HA6TRDJC5QN","created_at":"2026-07-05T10:19:27.569288+00:00"},{"alias_kind":"pith_short_8","alias_value":"O26T7HA6","created_at":"2026-07-05T10:19:27.569288+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12940","citing_title":"Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07080","citing_title":"dots.tts Technical Report","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00387","citing_title":"From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02631","citing_title":"Wavelet as Tokenizer: Preliminary Results on a Shared Wavelet Token Schema for Natural Signals","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30993","citing_title":"SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30940","citing_title":"Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":208,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30811","citing_title":"AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation","ref_index":23,"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":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":64,"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":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29488","citing_title":"AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20519","citing_title":"Codec-Robust Attacks on Audio LLMs","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03526","citing_title":"Enhancing Speech Large Language Models through Reinforced Behavior Alignment","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01537","citing_title":"Two-Dimensional Quantization for Geometry-Aware Audio Coding","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20519","citing_title":"Codec-Robust Attacks on Audio LLMs","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2505.24437","citing_title":"SwitchCodec: A High-Fidelity Nerual Audio Codec With Sparse Quantization","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2412.02612","citing_title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06870","citing_title":"Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11098","citing_title":"AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling","ref_index":20,"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":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05927","citing_title":"Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM","ref_index":42,"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":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06870","citing_title":"Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O26T7HA6TRDJC5QNIPHWIBMSYP","json":"https://pith.science/pith/O26T7HA6TRDJC5QNIPHWIBMSYP.json","graph_json":"https://pith.science/api/pith-number/O26T7HA6TRDJC5QNIPHWIBMSYP/graph.json","events_json":"https://pith.science/api/pith-number/O26T7HA6TRDJC5QNIPHWIBMSYP/events.json","paper":"https://pith.science/paper/O26T7HA6"},"agent_actions":{"view_html":"https://pith.science/pith/O26T7HA6TRDJC5QNIPHWIBMSYP","download_json":"https://pith.science/pith/O26T7HA6TRDJC5QNIPHWIBMSYP.json","view_paper":"https://pith.science/paper/O26T7HA6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.16532&json=true","fetch_graph":"https://pith.science/api/pith-number/O26T7HA6TRDJC5QNIPHWIBMSYP/graph.json","fetch_events":"https://pith.science/api/pith-number/O26T7HA6TRDJC5QNIPHWIBMSYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O26T7HA6TRDJC5QNIPHWIBMSYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O26T7HA6TRDJC5QNIPHWIBMSYP/action/storage_attestation","attest_author":"https://pith.science/pith/O26T7HA6TRDJC5QNIPHWIBMSYP/action/author_attestation","sign_citation":"https://pith.science/pith/O26T7HA6TRDJC5QNIPHWIBMSYP/action/citation_signature","submit_replication":"https://pith.science/pith/O26T7HA6TRDJC5QNIPHWIBMSYP/action/replication_record"}},"created_at":"2026-07-05T10:19:27.569288+00:00","updated_at":"2026-07-05T10:19:27.569288+00:00"}