{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KPBG7WMOFZCDE2ICAK7IYMONNH","short_pith_number":"pith:KPBG7WMO","schema_version":"1.0","canonical_sha256":"53c26fd98e2e4432690202be8c31cd69fa733fcb18cf0d1b08fe5eed14d4f2a1","source":{"kind":"arxiv","id":"2307.03183","version":1},"attestation_state":"computed","paper":{"title":"Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"James Glass, Leonid Karlinsky, Sameer Khurana, Yuan Gong","submitted_at":"2023-07-06T17:58:28Z","abstract_excerpt":"In this paper, we focus on Whisper, a recent automatic speech recognition model trained with a massive 680k hour labeled speech corpus recorded in diverse conditions. We first show an interesting finding that while Whisper is very robust against real-world background sounds (e.g., music), its audio representation is actually not noise-invariant, but is instead highly correlated to non-speech sounds, indicating that Whisper recognizes speech conditioned on the noise type. With this finding, we build a unified audio tagging and speech recognition model Whisper-AT by freezing the backbone of Whis"},"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":"2307.03183","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-06T17:58:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e0bd8f97dfdbbfe131acb1efa31474fcde77f719c88e7e7ef2ef818d2d5fdcda","abstract_canon_sha256":"d7cf02a0cc8ecaeabc9b54690e16407dda7005d67d74cdb1e1102ead9436c878"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:11.620299Z","signature_b64":"p5YcsG6DuWQPtU5BYm+wp8A7XVwybXUy5EQsDi7bjFrKrrnqcdJyG5x4rWmPhm2LiXcFjqnkinGBHc0kubyTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53c26fd98e2e4432690202be8c31cd69fa733fcb18cf0d1b08fe5eed14d4f2a1","last_reissued_at":"2026-07-05T06:58:11.619761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:11.619761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"James Glass, Leonid Karlinsky, Sameer Khurana, Yuan Gong","submitted_at":"2023-07-06T17:58:28Z","abstract_excerpt":"In this paper, we focus on Whisper, a recent automatic speech recognition model trained with a massive 680k hour labeled speech corpus recorded in diverse conditions. We first show an interesting finding that while Whisper is very robust against real-world background sounds (e.g., music), its audio representation is actually not noise-invariant, but is instead highly correlated to non-speech sounds, indicating that Whisper recognizes speech conditioned on the noise type. With this finding, we build a unified audio tagging and speech recognition model Whisper-AT by freezing the backbone of Whis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03183","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/2307.03183/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":"2307.03183","created_at":"2026-07-05T06:58:11.619819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.03183v1","created_at":"2026-07-05T06:58:11.619819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03183","created_at":"2026-07-05T06:58:11.619819+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPBG7WMOFZCD","created_at":"2026-07-05T06:58:11.619819+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPBG7WMOFZCDE2IC","created_at":"2026-07-05T06:58:11.619819+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPBG7WMO","created_at":"2026-07-05T06:58:11.619819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05365","citing_title":"SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPBG7WMOFZCDE2ICAK7IYMONNH","json":"https://pith.science/pith/KPBG7WMOFZCDE2ICAK7IYMONNH.json","graph_json":"https://pith.science/api/pith-number/KPBG7WMOFZCDE2ICAK7IYMONNH/graph.json","events_json":"https://pith.science/api/pith-number/KPBG7WMOFZCDE2ICAK7IYMONNH/events.json","paper":"https://pith.science/paper/KPBG7WMO"},"agent_actions":{"view_html":"https://pith.science/pith/KPBG7WMOFZCDE2ICAK7IYMONNH","download_json":"https://pith.science/pith/KPBG7WMOFZCDE2ICAK7IYMONNH.json","view_paper":"https://pith.science/paper/KPBG7WMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.03183&json=true","fetch_graph":"https://pith.science/api/pith-number/KPBG7WMOFZCDE2ICAK7IYMONNH/graph.json","fetch_events":"https://pith.science/api/pith-number/KPBG7WMOFZCDE2ICAK7IYMONNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPBG7WMOFZCDE2ICAK7IYMONNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPBG7WMOFZCDE2ICAK7IYMONNH/action/storage_attestation","attest_author":"https://pith.science/pith/KPBG7WMOFZCDE2ICAK7IYMONNH/action/author_attestation","sign_citation":"https://pith.science/pith/KPBG7WMOFZCDE2ICAK7IYMONNH/action/citation_signature","submit_replication":"https://pith.science/pith/KPBG7WMOFZCDE2ICAK7IYMONNH/action/replication_record"}},"created_at":"2026-07-05T06:58:11.619819+00:00","updated_at":"2026-07-05T06:58:11.619819+00:00"}