{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GGD75DDZTF24GHQ3ALY2GNSGRM","short_pith_number":"pith:GGD75DDZ","schema_version":"1.0","canonical_sha256":"3187fe8c799975c31e1b02f1a336468b04a5de88eb008e40c8f6069ce9e38c42","source":{"kind":"arxiv","id":"2310.02720","version":2},"attestation_state":"computed","paper":{"title":"Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Anna Sun, Hirofumi Inaguma, Ilia Kulikov, Jiatong Shi, Xutai Ma","submitted_at":"2023-10-04T10:52:13Z","abstract_excerpt":"Existing Self-Supervised Learning (SSL) models for speech typically process speech signals at a fixed resolution of 20 milliseconds. This approach overlooks the varying informational content present at different resolutions in speech signals. In contrast, this paper aims to incorporate multi-resolution information into speech self-supervised representation learning. We introduce a SSL model that leverages a hierarchical Transformer architecture, complemented by HuBERT-style masked prediction objectives, to process speech at multiple resolutions. Experimental results indicate that the proposed "},"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":"2310.02720","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-10-04T10:52:13Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"fa8fdde89d22d45c47e64f029f98683901f962e5669e057dee94dc3d3b06577e","abstract_canon_sha256":"fd8ffbf1a08b785005d4bcc4802f4ba78dd6169bf9b45787fe03012f9f8497a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:52.723857Z","signature_b64":"y4NBENUwM9I5SouHwomhVpIWZVD8IdeIwHeYdrmD2xeQqzGRiqrraCUegYELd8GCBAp0Zd0RguKj3j8IwJljDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3187fe8c799975c31e1b02f1a336468b04a5de88eb008e40c8f6069ce9e38c42","last_reissued_at":"2026-07-05T07:38:52.723292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:52.723292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Anna Sun, Hirofumi Inaguma, Ilia Kulikov, Jiatong Shi, Xutai Ma","submitted_at":"2023-10-04T10:52:13Z","abstract_excerpt":"Existing Self-Supervised Learning (SSL) models for speech typically process speech signals at a fixed resolution of 20 milliseconds. This approach overlooks the varying informational content present at different resolutions in speech signals. In contrast, this paper aims to incorporate multi-resolution information into speech self-supervised representation learning. We introduce a SSL model that leverages a hierarchical Transformer architecture, complemented by HuBERT-style masked prediction objectives, to process speech at multiple resolutions. Experimental results indicate that the proposed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02720","kind":"arxiv","version":2},"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/2310.02720/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":"2310.02720","created_at":"2026-07-05T07:38:52.723356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02720v2","created_at":"2026-07-05T07:38:52.723356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02720","created_at":"2026-07-05T07:38:52.723356+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGD75DDZTF24","created_at":"2026-07-05T07:38:52.723356+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGD75DDZTF24GHQ3","created_at":"2026-07-05T07:38:52.723356+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGD75DDZ","created_at":"2026-07-05T07:38:52.723356+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00988","citing_title":"A Unified Denoising and Adaptation Framework for Self-Supervised Bengali Dialectal ASR","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGD75DDZTF24GHQ3ALY2GNSGRM","json":"https://pith.science/pith/GGD75DDZTF24GHQ3ALY2GNSGRM.json","graph_json":"https://pith.science/api/pith-number/GGD75DDZTF24GHQ3ALY2GNSGRM/graph.json","events_json":"https://pith.science/api/pith-number/GGD75DDZTF24GHQ3ALY2GNSGRM/events.json","paper":"https://pith.science/paper/GGD75DDZ"},"agent_actions":{"view_html":"https://pith.science/pith/GGD75DDZTF24GHQ3ALY2GNSGRM","download_json":"https://pith.science/pith/GGD75DDZTF24GHQ3ALY2GNSGRM.json","view_paper":"https://pith.science/paper/GGD75DDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02720&json=true","fetch_graph":"https://pith.science/api/pith-number/GGD75DDZTF24GHQ3ALY2GNSGRM/graph.json","fetch_events":"https://pith.science/api/pith-number/GGD75DDZTF24GHQ3ALY2GNSGRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGD75DDZTF24GHQ3ALY2GNSGRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGD75DDZTF24GHQ3ALY2GNSGRM/action/storage_attestation","attest_author":"https://pith.science/pith/GGD75DDZTF24GHQ3ALY2GNSGRM/action/author_attestation","sign_citation":"https://pith.science/pith/GGD75DDZTF24GHQ3ALY2GNSGRM/action/citation_signature","submit_replication":"https://pith.science/pith/GGD75DDZTF24GHQ3ALY2GNSGRM/action/replication_record"}},"created_at":"2026-07-05T07:38:52.723356+00:00","updated_at":"2026-07-05T07:38:52.723356+00:00"}