{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QPNNBTJO3SHC7SZLOU7D7WKLQ6","short_pith_number":"pith:QPNNBTJO","schema_version":"1.0","canonical_sha256":"83dad0cd2edc8e2fcb2b753e3fd94b87b7db5a0bf615965665c3be300ceacffa","source":{"kind":"arxiv","id":"2305.17356","version":1},"attestation_state":"computed","paper":{"title":"Bridging the Granularity Gap for Acoustic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anxiang Ma, Chengbo Jiao, Chen Xu, Chi Hu, Huizhen Wang, Jingbo Zhu, Tong Xiao, Xiaoqian Liu, Xin Zeng, Yuhao Zhang","submitted_at":"2023-05-27T03:52:52Z","abstract_excerpt":"While Transformer has become the de-facto standard for speech, modeling upon the fine-grained frame-level features remains an open challenge of capturing long-distance dependencies and distributing the attention weights. We propose \\textit{Progressive Down-Sampling} (PDS) which gradually compresses the acoustic features into coarser-grained units containing more complete semantic information, like text-level representation. In addition, we develop a representation fusion method to alleviate information loss that occurs inevitably during high compression. In this way, we compress the acoustic f"},"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":"2305.17356","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-27T03:52:52Z","cross_cats_sorted":[],"title_canon_sha256":"6a3605d04199e8d52c4010ff77e3545d025b55f915ff94706168e65a85cf521e","abstract_canon_sha256":"89e7f11056c082d8193e011768e1f4f7b8d527e1879da424079c84be51cba02d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:26.866562Z","signature_b64":"V6EgDxe9ujV+l5w3qwzaXprkpURLT49Xauk0sOSNeJtqAFuwZTeBjeco0xYMRMF49jLsuxrWWkAjDgVrZVKVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83dad0cd2edc8e2fcb2b753e3fd94b87b7db5a0bf615965665c3be300ceacffa","last_reissued_at":"2026-07-05T06:14:26.866082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:26.866082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Granularity Gap for Acoustic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anxiang Ma, Chengbo Jiao, Chen Xu, Chi Hu, Huizhen Wang, Jingbo Zhu, Tong Xiao, Xiaoqian Liu, Xin Zeng, Yuhao Zhang","submitted_at":"2023-05-27T03:52:52Z","abstract_excerpt":"While Transformer has become the de-facto standard for speech, modeling upon the fine-grained frame-level features remains an open challenge of capturing long-distance dependencies and distributing the attention weights. We propose \\textit{Progressive Down-Sampling} (PDS) which gradually compresses the acoustic features into coarser-grained units containing more complete semantic information, like text-level representation. In addition, we develop a representation fusion method to alleviate information loss that occurs inevitably during high compression. In this way, we compress the acoustic f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17356","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/2305.17356/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":"2305.17356","created_at":"2026-07-05T06:14:26.866147+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17356v1","created_at":"2026-07-05T06:14:26.866147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17356","created_at":"2026-07-05T06:14:26.866147+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPNNBTJO3SHC","created_at":"2026-07-05T06:14:26.866147+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPNNBTJO3SHC7SZL","created_at":"2026-07-05T06:14:26.866147+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPNNBTJO","created_at":"2026-07-05T06:14:26.866147+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/QPNNBTJO3SHC7SZLOU7D7WKLQ6","json":"https://pith.science/pith/QPNNBTJO3SHC7SZLOU7D7WKLQ6.json","graph_json":"https://pith.science/api/pith-number/QPNNBTJO3SHC7SZLOU7D7WKLQ6/graph.json","events_json":"https://pith.science/api/pith-number/QPNNBTJO3SHC7SZLOU7D7WKLQ6/events.json","paper":"https://pith.science/paper/QPNNBTJO"},"agent_actions":{"view_html":"https://pith.science/pith/QPNNBTJO3SHC7SZLOU7D7WKLQ6","download_json":"https://pith.science/pith/QPNNBTJO3SHC7SZLOU7D7WKLQ6.json","view_paper":"https://pith.science/paper/QPNNBTJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17356&json=true","fetch_graph":"https://pith.science/api/pith-number/QPNNBTJO3SHC7SZLOU7D7WKLQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/QPNNBTJO3SHC7SZLOU7D7WKLQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPNNBTJO3SHC7SZLOU7D7WKLQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPNNBTJO3SHC7SZLOU7D7WKLQ6/action/storage_attestation","attest_author":"https://pith.science/pith/QPNNBTJO3SHC7SZLOU7D7WKLQ6/action/author_attestation","sign_citation":"https://pith.science/pith/QPNNBTJO3SHC7SZLOU7D7WKLQ6/action/citation_signature","submit_replication":"https://pith.science/pith/QPNNBTJO3SHC7SZLOU7D7WKLQ6/action/replication_record"}},"created_at":"2026-07-05T06:14:26.866147+00:00","updated_at":"2026-07-05T06:14:26.866147+00:00"}