{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:A2V2P5ZKUSHBDKS66H6ML42Z3K","short_pith_number":"pith:A2V2P5ZK","canonical_record":{"source":{"id":"2412.18566","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T17:37:11Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f0cf255d5a398c6bae788c6262e1417a0bb5622c1880eb9fa34310df1cf3eb31","abstract_canon_sha256":"93797f89a124ae816af674fde2c69f474999826d33b8006ea05e5f9fa0f2eeaf"},"schema_version":"1.0"},"canonical_sha256":"06aba7f72aa48e11aa5ef1fcc5f359daa34ee285daec05e4d159ee8f4e5eea0e","source":{"kind":"arxiv","id":"2412.18566","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18566","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18566v2","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18566","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"pith_short_12","alias_value":"A2V2P5ZKUSHB","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"pith_short_16","alias_value":"A2V2P5ZKUSHBDKS6","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"pith_short_8","alias_value":"A2V2P5ZK","created_at":"2026-07-05T09:55:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:A2V2P5ZKUSHBDKS66H6ML42Z3K","target":"record","payload":{"canonical_record":{"source":{"id":"2412.18566","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T17:37:11Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f0cf255d5a398c6bae788c6262e1417a0bb5622c1880eb9fa34310df1cf3eb31","abstract_canon_sha256":"93797f89a124ae816af674fde2c69f474999826d33b8006ea05e5f9fa0f2eeaf"},"schema_version":"1.0"},"canonical_sha256":"06aba7f72aa48e11aa5ef1fcc5f359daa34ee285daec05e4d159ee8f4e5eea0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:36.141891Z","signature_b64":"gliBayM151hBx3v1FTz882C1rxXOEq5rbqBScwIlvGyvxbS3U6UVUC3pLHOpXE9hGn/7J62jCoCwRAa8JNGGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06aba7f72aa48e11aa5ef1fcc5f359daa34ee285daec05e4d159ee8f4e5eea0e","last_reissued_at":"2026-07-05T09:55:36.141349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:36.141349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.18566","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:55:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ak63uHwI7YY2nrg8jJ8wa/IJhbKkiABWNprxD/E+6sIEPwrVHfXN7Qs1ubRim8Ac0xvLEDJLCW6mwrZxJbERCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:56:47.095150Z"},"content_sha256":"69773e9903931f96a986413519d9ad66049894a347666e4116b21e420e347a5b","schema_version":"1.0","event_id":"sha256:69773e9903931f96a986413519d9ad66049894a347666e4116b21e420e347a5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:A2V2P5ZKUSHBDKS66H6ML42Z3K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-resource Speech Translation and Recognition with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Anshu Bhatia, Brady Houston, Daniel Garcia-Romero, Goeric Huybrechts, Karel Mundnich, Katrin Kirchhoff, Kyu J. Han, Nilaksh Das, Prashant Mathur, Srikanth Ronanki, Veera Raghavendra Elluru, Xing Niu, Zejiang Hou","submitted_at":"2024-12-24T17:37:11Z","abstract_excerpt":"Despite recent advancements in speech processing, zero-resource speech translation (ST) and automatic speech recognition (ASR) remain challenging problems. In this work, we propose to leverage a multilingual Large Language Model (LLM) to perform ST and ASR in languages for which the model has never seen paired audio-text data. We achieve this by using a pre-trained multilingual speech encoder, a multilingual LLM, and a lightweight adaptation module that maps the audio representations to the token embedding space of the LLM. We perform several experiments both in ST and ASR to understand how to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18566","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/2412.18566/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:55:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+8Muf6EFOOJVZNjXgn8ihB6Cwlhu+vuwIDMFX4/yI/E9RsyNQ9YhLbo6YsIV4vWuP0WkuESvFS5BvEfK/xWHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:56:47.095779Z"},"content_sha256":"bcda3d4d7daa85d92a80befa06595a58d21ca4bc791580c4f7d2af6aa799a661","schema_version":"1.0","event_id":"sha256:bcda3d4d7daa85d92a80befa06595a58d21ca4bc791580c4f7d2af6aa799a661"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A2V2P5ZKUSHBDKS66H6ML42Z3K/bundle.json","state_url":"https://pith.science/pith/A2V2P5ZKUSHBDKS66H6ML42Z3K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A2V2P5ZKUSHBDKS66H6ML42Z3K/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T18:56:47Z","links":{"resolver":"https://pith.science/pith/A2V2P5ZKUSHBDKS66H6ML42Z3K","bundle":"https://pith.science/pith/A2V2P5ZKUSHBDKS66H6ML42Z3K/bundle.json","state":"https://pith.science/pith/A2V2P5ZKUSHBDKS66H6ML42Z3K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A2V2P5ZKUSHBDKS66H6ML42Z3K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A2V2P5ZKUSHBDKS66H6ML42Z3K","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"93797f89a124ae816af674fde2c69f474999826d33b8006ea05e5f9fa0f2eeaf","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T17:37:11Z","title_canon_sha256":"f0cf255d5a398c6bae788c6262e1417a0bb5622c1880eb9fa34310df1cf3eb31"},"schema_version":"1.0","source":{"id":"2412.18566","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18566","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18566v2","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18566","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"pith_short_12","alias_value":"A2V2P5ZKUSHB","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"pith_short_16","alias_value":"A2V2P5ZKUSHBDKS6","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"pith_short_8","alias_value":"A2V2P5ZK","created_at":"2026-07-05T09:55:36Z"}],"graph_snapshots":[{"event_id":"sha256:bcda3d4d7daa85d92a80befa06595a58d21ca4bc791580c4f7d2af6aa799a661","target":"graph","created_at":"2026-07-05T09:55:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.18566/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advancements in speech processing, zero-resource speech translation (ST) and automatic speech recognition (ASR) remain challenging problems. In this work, we propose to leverage a multilingual Large Language Model (LLM) to perform ST and ASR in languages for which the model has never seen paired audio-text data. We achieve this by using a pre-trained multilingual speech encoder, a multilingual LLM, and a lightweight adaptation module that maps the audio representations to the token embedding space of the LLM. We perform several experiments both in ST and ASR to understand how to","authors_text":"Anshu Bhatia, Brady Houston, Daniel Garcia-Romero, Goeric Huybrechts, Karel Mundnich, Katrin Kirchhoff, Kyu J. Han, Nilaksh Das, Prashant Mathur, Srikanth Ronanki, Veera Raghavendra Elluru, Xing Niu, Zejiang Hou","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T17:37:11Z","title":"Zero-resource Speech Translation and Recognition with LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18566","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:69773e9903931f96a986413519d9ad66049894a347666e4116b21e420e347a5b","target":"record","created_at":"2026-07-05T09:55:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"93797f89a124ae816af674fde2c69f474999826d33b8006ea05e5f9fa0f2eeaf","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T17:37:11Z","title_canon_sha256":"f0cf255d5a398c6bae788c6262e1417a0bb5622c1880eb9fa34310df1cf3eb31"},"schema_version":"1.0","source":{"id":"2412.18566","kind":"arxiv","version":2}},"canonical_sha256":"06aba7f72aa48e11aa5ef1fcc5f359daa34ee285daec05e4d159ee8f4e5eea0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06aba7f72aa48e11aa5ef1fcc5f359daa34ee285daec05e4d159ee8f4e5eea0e","first_computed_at":"2026-07-05T09:55:36.141349Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:36.141349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gliBayM151hBx3v1FTz882C1rxXOEq5rbqBScwIlvGyvxbS3U6UVUC3pLHOpXE9hGn/7J62jCoCwRAa8JNGGBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:36.141891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18566","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69773e9903931f96a986413519d9ad66049894a347666e4116b21e420e347a5b","sha256:bcda3d4d7daa85d92a80befa06595a58d21ca4bc791580c4f7d2af6aa799a661"],"state_sha256":"f3ba77583c9f72e526772f342682941da5a8fe50bb6db5a5d4890d4e55f6567a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Mzzz+RVFncUQxI7X4GB70fbb3DHj8FlyXU6PFCu4bLiVcPWF0efrSBxXQjIY4Nz2eBdktZ3IdNDmLLxzugYBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:56:47.099788Z","bundle_sha256":"bb32c04181abac67c53f8ba7e622562526f9f53ba537fc31615a4a62f4065bf1"}}