{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GH6M7HH7GHRIMVLD2WTY3WNCYQ","short_pith_number":"pith:GH6M7HH7","schema_version":"1.0","canonical_sha256":"31fccf9cff31e2865563d5a78dd9a2c43a504864c5c1e3e42b1c89b45192714e","source":{"kind":"arxiv","id":"1702.03856","version":1},"attestation_state":"computed","paper":{"title":"Towards speech-to-text translation without speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Lopez, Herman Kamper, Sameer Bansal, Sharon Goldwater","submitted_at":"2017-02-13T16:30:23Z","abstract_excerpt":"We explore the problem of translating speech to text in low-resource scenarios where neither automatic speech recognition (ASR) nor machine translation (MT) are available, but we have training data in the form of audio paired with text translations. We present the first system for this problem applied to a realistic multi-speaker dataset, the CALLHOME Spanish-English speech translation corpus. Our approach uses unsupervised term discovery (UTD) to cluster repeated patterns in the audio, creating a pseudotext, which we pair with translations to create a parallel text and train a simple bag-of-w"},"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":"1702.03856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-13T16:30:23Z","cross_cats_sorted":[],"title_canon_sha256":"5ab3cbb9d9b1756c0e712d93152b10e34cf9171e40e55d240b49e0e4a8f259c8","abstract_canon_sha256":"adb85d1167cc93e6c68e4d838f63625485809c2b8541a46a4a7f35c6581d5cd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:52.865404Z","signature_b64":"APg4tn53Y1DrFUKOIkKeuQhX2fLtsn9vkmNPXbGizeUZ9Z0GMJ2k9TH7R533vsSbBmzMx8vw18BOwcMDa7Q8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31fccf9cff31e2865563d5a78dd9a2c43a504864c5c1e3e42b1c89b45192714e","last_reissued_at":"2026-05-18T00:50:52.864933Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:52.864933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards speech-to-text translation without speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Lopez, Herman Kamper, Sameer Bansal, Sharon Goldwater","submitted_at":"2017-02-13T16:30:23Z","abstract_excerpt":"We explore the problem of translating speech to text in low-resource scenarios where neither automatic speech recognition (ASR) nor machine translation (MT) are available, but we have training data in the form of audio paired with text translations. We present the first system for this problem applied to a realistic multi-speaker dataset, the CALLHOME Spanish-English speech translation corpus. Our approach uses unsupervised term discovery (UTD) to cluster repeated patterns in the audio, creating a pseudotext, which we pair with translations to create a parallel text and train a simple bag-of-w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.03856","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":"1702.03856","created_at":"2026-05-18T00:50:52.865021+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.03856v1","created_at":"2026-05-18T00:50:52.865021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.03856","created_at":"2026-05-18T00:50:52.865021+00:00"},{"alias_kind":"pith_short_12","alias_value":"GH6M7HH7GHRI","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"GH6M7HH7GHRIMVLD","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"GH6M7HH7","created_at":"2026-05-18T12:31:15.632608+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/GH6M7HH7GHRIMVLD2WTY3WNCYQ","json":"https://pith.science/pith/GH6M7HH7GHRIMVLD2WTY3WNCYQ.json","graph_json":"https://pith.science/api/pith-number/GH6M7HH7GHRIMVLD2WTY3WNCYQ/graph.json","events_json":"https://pith.science/api/pith-number/GH6M7HH7GHRIMVLD2WTY3WNCYQ/events.json","paper":"https://pith.science/paper/GH6M7HH7"},"agent_actions":{"view_html":"https://pith.science/pith/GH6M7HH7GHRIMVLD2WTY3WNCYQ","download_json":"https://pith.science/pith/GH6M7HH7GHRIMVLD2WTY3WNCYQ.json","view_paper":"https://pith.science/paper/GH6M7HH7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.03856&json=true","fetch_graph":"https://pith.science/api/pith-number/GH6M7HH7GHRIMVLD2WTY3WNCYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/GH6M7HH7GHRIMVLD2WTY3WNCYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GH6M7HH7GHRIMVLD2WTY3WNCYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GH6M7HH7GHRIMVLD2WTY3WNCYQ/action/storage_attestation","attest_author":"https://pith.science/pith/GH6M7HH7GHRIMVLD2WTY3WNCYQ/action/author_attestation","sign_citation":"https://pith.science/pith/GH6M7HH7GHRIMVLD2WTY3WNCYQ/action/citation_signature","submit_replication":"https://pith.science/pith/GH6M7HH7GHRIMVLD2WTY3WNCYQ/action/replication_record"}},"created_at":"2026-05-18T00:50:52.865021+00:00","updated_at":"2026-05-18T00:50:52.865021+00:00"}