{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LQ5A4IYFMYTIPBSK2DAUYCDVJY","short_pith_number":"pith:LQ5A4IYF","schema_version":"1.0","canonical_sha256":"5c3a0e2305662687864ad0c14c08754e3fc51275213b2ef572394ed4fb2eb0da","source":{"kind":"arxiv","id":"2502.05356","version":1},"attestation_state":"computed","paper":{"title":"Distillation and Pruning for Scalable Self-Supervised Representation-Based Speech Quality Assessment","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Benjamin Stahl, Hannes Gamper","submitted_at":"2025-02-07T22:08:12Z","abstract_excerpt":"In this paper, we investigate distillation and pruning methods to reduce model size for non-intrusive speech quality assessment based on self-supervised representations. Our experiments build on XLS-R-SQA, a speech quality assessment model using wav2vec 2.0 XLS-R embeddings. We retrain this model on a large compilation of mean opinion score datasets, encompassing over 100,000 labeled clips. For distillation, using this model as a teacher, we generate pseudo-labels on unlabeled degraded speech signals and train student models of varying sizes. For pruning, we use a data-driven strategy. While d"},"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":"2502.05356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-07T22:08:12Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"236de149e0bc2810f951e9eff9c213b0deddd11514ffa738c5f635e32c7cafae","abstract_canon_sha256":"246620e2f9f22e2035c251d75f12a3c549f189b077976e0f4a6e067bd5cb0665"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:36.827694Z","signature_b64":"mnoS9ajp0LUtjQb33luG90DxD7g8PcV73sHLaFBiRgoeN7HIgPJxn1b9uDqm8xN7DkakRxub7xEY/EVjODTgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c3a0e2305662687864ad0c14c08754e3fc51275213b2ef572394ed4fb2eb0da","last_reissued_at":"2026-07-05T10:11:36.827237Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:36.827237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distillation and Pruning for Scalable Self-Supervised Representation-Based Speech Quality Assessment","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Benjamin Stahl, Hannes Gamper","submitted_at":"2025-02-07T22:08:12Z","abstract_excerpt":"In this paper, we investigate distillation and pruning methods to reduce model size for non-intrusive speech quality assessment based on self-supervised representations. Our experiments build on XLS-R-SQA, a speech quality assessment model using wav2vec 2.0 XLS-R embeddings. We retrain this model on a large compilation of mean opinion score datasets, encompassing over 100,000 labeled clips. For distillation, using this model as a teacher, we generate pseudo-labels on unlabeled degraded speech signals and train student models of varying sizes. For pruning, we use a data-driven strategy. While d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05356","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/2502.05356/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":"2502.05356","created_at":"2026-07-05T10:11:36.827285+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05356v1","created_at":"2026-07-05T10:11:36.827285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05356","created_at":"2026-07-05T10:11:36.827285+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQ5A4IYFMYTI","created_at":"2026-07-05T10:11:36.827285+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQ5A4IYFMYTIPBSK","created_at":"2026-07-05T10:11:36.827285+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQ5A4IYF","created_at":"2026-07-05T10:11:36.827285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23332","citing_title":"Don't Listen to Me: A Lightweight, Low-Latency Model for Own-Voice Cancellation in Far-Field Speech Enhancement","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21933","citing_title":"ISCSLP 2026 CoT-TTS Challenge: Chain-of-Thought Reasoning for Context-Aware Text-to-Speech","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQ5A4IYFMYTIPBSK2DAUYCDVJY","json":"https://pith.science/pith/LQ5A4IYFMYTIPBSK2DAUYCDVJY.json","graph_json":"https://pith.science/api/pith-number/LQ5A4IYFMYTIPBSK2DAUYCDVJY/graph.json","events_json":"https://pith.science/api/pith-number/LQ5A4IYFMYTIPBSK2DAUYCDVJY/events.json","paper":"https://pith.science/paper/LQ5A4IYF"},"agent_actions":{"view_html":"https://pith.science/pith/LQ5A4IYFMYTIPBSK2DAUYCDVJY","download_json":"https://pith.science/pith/LQ5A4IYFMYTIPBSK2DAUYCDVJY.json","view_paper":"https://pith.science/paper/LQ5A4IYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05356&json=true","fetch_graph":"https://pith.science/api/pith-number/LQ5A4IYFMYTIPBSK2DAUYCDVJY/graph.json","fetch_events":"https://pith.science/api/pith-number/LQ5A4IYFMYTIPBSK2DAUYCDVJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQ5A4IYFMYTIPBSK2DAUYCDVJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQ5A4IYFMYTIPBSK2DAUYCDVJY/action/storage_attestation","attest_author":"https://pith.science/pith/LQ5A4IYFMYTIPBSK2DAUYCDVJY/action/author_attestation","sign_citation":"https://pith.science/pith/LQ5A4IYFMYTIPBSK2DAUYCDVJY/action/citation_signature","submit_replication":"https://pith.science/pith/LQ5A4IYFMYTIPBSK2DAUYCDVJY/action/replication_record"}},"created_at":"2026-07-05T10:11:36.827285+00:00","updated_at":"2026-07-05T10:11:36.827285+00:00"}