{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AN7HAAIKBGPUGNVU2RT2HH5A2F","short_pith_number":"pith:AN7HAAIK","schema_version":"1.0","canonical_sha256":"037e70010a099f4336b4d467a39fa0d15499f8f9f3fa410c2cb28f44cdbaeee5","source":{"kind":"arxiv","id":"1906.01199","version":1},"attestation_state":"computed","paper":{"title":"Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alan W Black, Elizabeth Salesky, Matthias Sperber","submitted_at":"2019-06-04T05:12:31Z","abstract_excerpt":"Previous work on end-to-end translation from speech has primarily used frame-level features as speech representations, which creates longer, sparser sequences than text. We show that a naive method to create compressed phoneme-like speech representations is far more effective and efficient for translation than traditional frame-level speech features. Specifically, we generate phoneme labels for speech frames and average consecutive frames with the same label to create shorter, higher-level source sequences for translation. We see improvements of up to 5 BLEU on both our high and low resource l"},"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":"1906.01199","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T05:12:31Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"00529f427100be11d7f2560e5c986eb91b36fb89a318f54e044f9d9cede6a64d","abstract_canon_sha256":"276aa2140e1178ef0692dd7e1d7ed5fe5a44c98a7a046ef792ad41ed409bcf4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:17.575201Z","signature_b64":"OpaO8uRxp8jNcrqDGs5kKrZw6ZHxnB2tWwe02EuXtoh1WbLwaqak1XT+0Ud/wB2AJKyWMR4+1F9QlKdS0ezOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"037e70010a099f4336b4d467a39fa0d15499f8f9f3fa410c2cb28f44cdbaeee5","last_reissued_at":"2026-05-17T23:44:17.574538Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:17.574538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alan W Black, Elizabeth Salesky, Matthias Sperber","submitted_at":"2019-06-04T05:12:31Z","abstract_excerpt":"Previous work on end-to-end translation from speech has primarily used frame-level features as speech representations, which creates longer, sparser sequences than text. We show that a naive method to create compressed phoneme-like speech representations is far more effective and efficient for translation than traditional frame-level speech features. Specifically, we generate phoneme labels for speech frames and average consecutive frames with the same label to create shorter, higher-level source sequences for translation. We see improvements of up to 5 BLEU on both our high and low resource l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01199","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":""},"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":"1906.01199","created_at":"2026-05-17T23:44:17.574647+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01199v1","created_at":"2026-05-17T23:44:17.574647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01199","created_at":"2026-05-17T23:44:17.574647+00:00"},{"alias_kind":"pith_short_12","alias_value":"AN7HAAIKBGPU","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"AN7HAAIKBGPUGNVU","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"AN7HAAIK","created_at":"2026-05-18T12:33:12.712433+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/AN7HAAIKBGPUGNVU2RT2HH5A2F","json":"https://pith.science/pith/AN7HAAIKBGPUGNVU2RT2HH5A2F.json","graph_json":"https://pith.science/api/pith-number/AN7HAAIKBGPUGNVU2RT2HH5A2F/graph.json","events_json":"https://pith.science/api/pith-number/AN7HAAIKBGPUGNVU2RT2HH5A2F/events.json","paper":"https://pith.science/paper/AN7HAAIK"},"agent_actions":{"view_html":"https://pith.science/pith/AN7HAAIKBGPUGNVU2RT2HH5A2F","download_json":"https://pith.science/pith/AN7HAAIKBGPUGNVU2RT2HH5A2F.json","view_paper":"https://pith.science/paper/AN7HAAIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01199&json=true","fetch_graph":"https://pith.science/api/pith-number/AN7HAAIKBGPUGNVU2RT2HH5A2F/graph.json","fetch_events":"https://pith.science/api/pith-number/AN7HAAIKBGPUGNVU2RT2HH5A2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AN7HAAIKBGPUGNVU2RT2HH5A2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AN7HAAIKBGPUGNVU2RT2HH5A2F/action/storage_attestation","attest_author":"https://pith.science/pith/AN7HAAIKBGPUGNVU2RT2HH5A2F/action/author_attestation","sign_citation":"https://pith.science/pith/AN7HAAIKBGPUGNVU2RT2HH5A2F/action/citation_signature","submit_replication":"https://pith.science/pith/AN7HAAIKBGPUGNVU2RT2HH5A2F/action/replication_record"}},"created_at":"2026-05-17T23:44:17.574647+00:00","updated_at":"2026-05-17T23:44:17.574647+00:00"}