{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GTAIBYWH7B2FVP43VQ4YSPICTK","short_pith_number":"pith:GTAIBYWH","schema_version":"1.0","canonical_sha256":"34c080e2c7f8745abf9bac39893d029ab1af9fdb7a229fb9a704a98c03a327d0","source":{"kind":"arxiv","id":"2509.10452","version":2},"attestation_state":"computed","paper":{"title":"WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Akshat Pandey, Karun Kumar, Raphael Tang","submitted_at":"2025-09-12T17:59:09Z","abstract_excerpt":"Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance. In many real-world settings, collecting speech data is impractical, necessitating text-only adaptation. We propose WhisTLE, a deeply supervised, text-only adaptation method for pretrained encoder-decoder ASR models. WhisTLE trains a variational autoencoder (VAE) to model encoder outputs from text and fine-tunes the decoder using the learned text-to-latent encoder, optionally combined with text-to-speech (TTS) adaptation. At inference, the original encode"},"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":"2509.10452","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T17:59:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7ca5a86b2c84d20aa0f8561252a79210eff87797d222910909b360f59154ccf7","abstract_canon_sha256":"5e0faa65ea52a02ae645c326d44992757595f3ea8fbab66b71bec070bc31cf69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:01.979325Z","signature_b64":"MFvU9G1ti/UITPPXAwYkyrRcjvftcquqCv94fI4JEaz2P6EM80f/CLV7aOsNbuBH8NBj81cwoSbq4AoAb7lbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34c080e2c7f8745abf9bac39893d029ab1af9fdb7a229fb9a704a98c03a327d0","last_reissued_at":"2026-05-26T02:05:01.978542Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:01.978542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Akshat Pandey, Karun Kumar, Raphael Tang","submitted_at":"2025-09-12T17:59:09Z","abstract_excerpt":"Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance. In many real-world settings, collecting speech data is impractical, necessitating text-only adaptation. We propose WhisTLE, a deeply supervised, text-only adaptation method for pretrained encoder-decoder ASR models. WhisTLE trains a variational autoencoder (VAE) to model encoder outputs from text and fine-tunes the decoder using the learned text-to-latent encoder, optionally combined with text-to-speech (TTS) adaptation. At inference, the original encode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10452","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/2509.10452/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":"2509.10452","created_at":"2026-05-26T02:05:01.978648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.10452v2","created_at":"2026-05-26T02:05:01.978648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10452","created_at":"2026-05-26T02:05:01.978648+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTAIBYWH7B2F","created_at":"2026-05-26T02:05:01.978648+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTAIBYWH7B2FVP43","created_at":"2026-05-26T02:05:01.978648+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTAIBYWH","created_at":"2026-05-26T02:05:01.978648+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/GTAIBYWH7B2FVP43VQ4YSPICTK","json":"https://pith.science/pith/GTAIBYWH7B2FVP43VQ4YSPICTK.json","graph_json":"https://pith.science/api/pith-number/GTAIBYWH7B2FVP43VQ4YSPICTK/graph.json","events_json":"https://pith.science/api/pith-number/GTAIBYWH7B2FVP43VQ4YSPICTK/events.json","paper":"https://pith.science/paper/GTAIBYWH"},"agent_actions":{"view_html":"https://pith.science/pith/GTAIBYWH7B2FVP43VQ4YSPICTK","download_json":"https://pith.science/pith/GTAIBYWH7B2FVP43VQ4YSPICTK.json","view_paper":"https://pith.science/paper/GTAIBYWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.10452&json=true","fetch_graph":"https://pith.science/api/pith-number/GTAIBYWH7B2FVP43VQ4YSPICTK/graph.json","fetch_events":"https://pith.science/api/pith-number/GTAIBYWH7B2FVP43VQ4YSPICTK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTAIBYWH7B2FVP43VQ4YSPICTK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTAIBYWH7B2FVP43VQ4YSPICTK/action/storage_attestation","attest_author":"https://pith.science/pith/GTAIBYWH7B2FVP43VQ4YSPICTK/action/author_attestation","sign_citation":"https://pith.science/pith/GTAIBYWH7B2FVP43VQ4YSPICTK/action/citation_signature","submit_replication":"https://pith.science/pith/GTAIBYWH7B2FVP43VQ4YSPICTK/action/replication_record"}},"created_at":"2026-05-26T02:05:01.978648+00:00","updated_at":"2026-05-26T02:05:01.978648+00:00"}