{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MLKG4JGWXOFHWRG2KGZXLBUEJM","short_pith_number":"pith:MLKG4JGW","schema_version":"1.0","canonical_sha256":"62d46e24d6bb8a7b44da51b37586844b0b92a7ec15acf63b840190eb6b8f9400","source":{"kind":"arxiv","id":"2011.10469","version":1},"attestation_state":"computed","paper":{"title":"Empirical Evaluation of Deep Learning Model Compression Techniques on the WaveNet Vocoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Giuseppe Coccia, Julian Mack, Sam Davis, Sam Gooch","submitted_at":"2020-11-20T16:01:56Z","abstract_excerpt":"WaveNet is a state-of-the-art text-to-speech vocoder that remains challenging to deploy due to its autoregressive loop. In this work we focus on ways to accelerate the original WaveNet architecture directly, as opposed to modifying the architecture, such that the model can be deployed as part of a scalable text-to-speech system. We survey a wide variety of model compression techniques that are amenable to deployment on a range of hardware platforms. In particular, we compare different model sparsity methods and levels, and seven widely used precisions as targets for quantization; and are able "},"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":"2011.10469","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-20T16:01:56Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"3d70fd8a2d06a5852c3274303002b5ed3ed78bb5b04ec6d273e504d51ad6e24a","abstract_canon_sha256":"5b261ce751042d03121c9612af9d2ee70a8764358ebec4e48394c298c20bf867"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:15.400322Z","signature_b64":"EfaCG/+ltawYt3uK1rttLc77IOcpRDJ/BBPwMS1+YJBbaKl8vsum7X7kcZkK1/Rw5xVGBzUeIN36GBD7uh5DCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62d46e24d6bb8a7b44da51b37586844b0b92a7ec15acf63b840190eb6b8f9400","last_reissued_at":"2026-07-05T01:53:15.399932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:15.399932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empirical Evaluation of Deep Learning Model Compression Techniques on the WaveNet Vocoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Giuseppe Coccia, Julian Mack, Sam Davis, Sam Gooch","submitted_at":"2020-11-20T16:01:56Z","abstract_excerpt":"WaveNet is a state-of-the-art text-to-speech vocoder that remains challenging to deploy due to its autoregressive loop. In this work we focus on ways to accelerate the original WaveNet architecture directly, as opposed to modifying the architecture, such that the model can be deployed as part of a scalable text-to-speech system. We survey a wide variety of model compression techniques that are amenable to deployment on a range of hardware platforms. In particular, we compare different model sparsity methods and levels, and seven widely used precisions as targets for quantization; and are able "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.10469","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/2011.10469/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":"2011.10469","created_at":"2026-07-05T01:53:15.399987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.10469v1","created_at":"2026-07-05T01:53:15.399987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.10469","created_at":"2026-07-05T01:53:15.399987+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLKG4JGWXOFH","created_at":"2026-07-05T01:53:15.399987+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLKG4JGWXOFHWRG2","created_at":"2026-07-05T01:53:15.399987+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLKG4JGW","created_at":"2026-07-05T01:53:15.399987+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/MLKG4JGWXOFHWRG2KGZXLBUEJM","json":"https://pith.science/pith/MLKG4JGWXOFHWRG2KGZXLBUEJM.json","graph_json":"https://pith.science/api/pith-number/MLKG4JGWXOFHWRG2KGZXLBUEJM/graph.json","events_json":"https://pith.science/api/pith-number/MLKG4JGWXOFHWRG2KGZXLBUEJM/events.json","paper":"https://pith.science/paper/MLKG4JGW"},"agent_actions":{"view_html":"https://pith.science/pith/MLKG4JGWXOFHWRG2KGZXLBUEJM","download_json":"https://pith.science/pith/MLKG4JGWXOFHWRG2KGZXLBUEJM.json","view_paper":"https://pith.science/paper/MLKG4JGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.10469&json=true","fetch_graph":"https://pith.science/api/pith-number/MLKG4JGWXOFHWRG2KGZXLBUEJM/graph.json","fetch_events":"https://pith.science/api/pith-number/MLKG4JGWXOFHWRG2KGZXLBUEJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLKG4JGWXOFHWRG2KGZXLBUEJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLKG4JGWXOFHWRG2KGZXLBUEJM/action/storage_attestation","attest_author":"https://pith.science/pith/MLKG4JGWXOFHWRG2KGZXLBUEJM/action/author_attestation","sign_citation":"https://pith.science/pith/MLKG4JGWXOFHWRG2KGZXLBUEJM/action/citation_signature","submit_replication":"https://pith.science/pith/MLKG4JGWXOFHWRG2KGZXLBUEJM/action/replication_record"}},"created_at":"2026-07-05T01:53:15.399987+00:00","updated_at":"2026-07-05T01:53:15.399987+00:00"}