{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4SJL6QAU4CMCM6NKHRZHK37AGY","short_pith_number":"pith:4SJL6QAU","schema_version":"1.0","canonical_sha256":"e492bf4014e0982679aa3c72756fe03611e5c35567c3ea9ee0d01d06c03bb7d4","source":{"kind":"arxiv","id":"2606.24080","version":1},"attestation_state":"computed","paper":{"title":"Audio--Image Alignment as a Continued-Pretraining Stage Improves Low-Resource ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Nihar Desai, Prasanta Kumar Ghosh, Sujith Pulikodan","submitted_at":"2026-06-23T02:48:58Z","abstract_excerpt":"Thousands of languages are spoken worldwide, yet many remain under-resourced for Automatic Speech Recognition (ASR) due to the limited availability of high-quality transcribed speech data. Collecting accurate transcriptions is often costly and labor-intensive, particularly for low-resource languages. In this work, we investigate the use of aligned audio-image pairs to adapt pretrained audio encoders without requiring transcription data before supervised fine-tuning. Our proposed representation alignment stage is introduced between large-scale pretraining and supervised ASR fine-tuning. Specifi"},"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":"2606.24080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-23T02:48:58Z","cross_cats_sorted":[],"title_canon_sha256":"eb4821fe7ddd9957b82b7f62bf80f1de22f305ee8f6924e8b9936e797d798a91","abstract_canon_sha256":"31f1653130d17ec831b38f6eb18cb39662c02d7a8371f1476d66a349ad38b5e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:39.779830Z","signature_b64":"0/Jw5tAfvxaP06uZgExlRmbIt0ZqjUJLxp+/0VGp5gRurvBt5RYPOaE75TUX2O1Y2iD8pDNXUclT9aNLMbObDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e492bf4014e0982679aa3c72756fe03611e5c35567c3ea9ee0d01d06c03bb7d4","last_reissued_at":"2026-06-24T01:14:39.779447Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:39.779447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio--Image Alignment as a Continued-Pretraining Stage Improves Low-Resource ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Nihar Desai, Prasanta Kumar Ghosh, Sujith Pulikodan","submitted_at":"2026-06-23T02:48:58Z","abstract_excerpt":"Thousands of languages are spoken worldwide, yet many remain under-resourced for Automatic Speech Recognition (ASR) due to the limited availability of high-quality transcribed speech data. Collecting accurate transcriptions is often costly and labor-intensive, particularly for low-resource languages. In this work, we investigate the use of aligned audio-image pairs to adapt pretrained audio encoders without requiring transcription data before supervised fine-tuning. Our proposed representation alignment stage is introduced between large-scale pretraining and supervised ASR fine-tuning. Specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24080","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/2606.24080/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":"2606.24080","created_at":"2026-06-24T01:14:39.779507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24080v1","created_at":"2026-06-24T01:14:39.779507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24080","created_at":"2026-06-24T01:14:39.779507+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SJL6QAU4CMC","created_at":"2026-06-24T01:14:39.779507+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SJL6QAU4CMCM6NK","created_at":"2026-06-24T01:14:39.779507+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SJL6QAU","created_at":"2026-06-24T01:14:39.779507+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/4SJL6QAU4CMCM6NKHRZHK37AGY","json":"https://pith.science/pith/4SJL6QAU4CMCM6NKHRZHK37AGY.json","graph_json":"https://pith.science/api/pith-number/4SJL6QAU4CMCM6NKHRZHK37AGY/graph.json","events_json":"https://pith.science/api/pith-number/4SJL6QAU4CMCM6NKHRZHK37AGY/events.json","paper":"https://pith.science/paper/4SJL6QAU"},"agent_actions":{"view_html":"https://pith.science/pith/4SJL6QAU4CMCM6NKHRZHK37AGY","download_json":"https://pith.science/pith/4SJL6QAU4CMCM6NKHRZHK37AGY.json","view_paper":"https://pith.science/paper/4SJL6QAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24080&json=true","fetch_graph":"https://pith.science/api/pith-number/4SJL6QAU4CMCM6NKHRZHK37AGY/graph.json","fetch_events":"https://pith.science/api/pith-number/4SJL6QAU4CMCM6NKHRZHK37AGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SJL6QAU4CMCM6NKHRZHK37AGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SJL6QAU4CMCM6NKHRZHK37AGY/action/storage_attestation","attest_author":"https://pith.science/pith/4SJL6QAU4CMCM6NKHRZHK37AGY/action/author_attestation","sign_citation":"https://pith.science/pith/4SJL6QAU4CMCM6NKHRZHK37AGY/action/citation_signature","submit_replication":"https://pith.science/pith/4SJL6QAU4CMCM6NKHRZHK37AGY/action/replication_record"}},"created_at":"2026-06-24T01:14:39.779507+00:00","updated_at":"2026-06-24T01:14:39.779507+00:00"}