{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XLPO4AJTGBCFQREJUU4CICQIUN","short_pith_number":"pith:XLPO4AJT","schema_version":"1.0","canonical_sha256":"badeee01333044584489a538240a08a342583d63945771316742f4558b601651","source":{"kind":"arxiv","id":"2210.00259","version":1},"attestation_state":"computed","paper":{"title":"Pre-trained Speech Representations as Feature Extractors for Speech Quality Assessment in Online Conferencing Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bastiaan Tamm, Helena Balabin, Hugo Van hamme, Rik Vandenberghe","submitted_at":"2022-10-01T11:51:06Z","abstract_excerpt":"Speech quality in online conferencing applications is typically assessed through human judgements in the form of the mean opinion score (MOS) metric. Since such a labor-intensive approach is not feasible for large-scale speech quality assessments in most settings, the focus has shifted towards automated MOS prediction through end-to-end training of deep neural networks (DNN). Instead of training a network from scratch, we propose to leverage the speech representations from the pre-trained wav2vec-based XLS-R model. However, the number of parameters of such a model exceeds task-specific DNNs by"},"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":"2210.00259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-10-01T11:51:06Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"2481ebb7cb3933350e76a06f1c042265d7dead80bb67f448c618ec22004da087","abstract_canon_sha256":"cbb9574bcfcb54ac9bd4a80cd789e6f0c03ffbda5a006333e9765017664231b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:30.183743Z","signature_b64":"LCIsSA4UvOIrznhpx2TX2vHKQiqR7PTY4JC1Pd/RDV64MTOOmGjhrGGO71pITIBl2p78jb5HqMkNNQ9hhu8xCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"badeee01333044584489a538240a08a342583d63945771316742f4558b601651","last_reissued_at":"2026-07-05T05:02:30.183404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:30.183404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-trained Speech Representations as Feature Extractors for Speech Quality Assessment in Online Conferencing Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bastiaan Tamm, Helena Balabin, Hugo Van hamme, Rik Vandenberghe","submitted_at":"2022-10-01T11:51:06Z","abstract_excerpt":"Speech quality in online conferencing applications is typically assessed through human judgements in the form of the mean opinion score (MOS) metric. Since such a labor-intensive approach is not feasible for large-scale speech quality assessments in most settings, the focus has shifted towards automated MOS prediction through end-to-end training of deep neural networks (DNN). Instead of training a network from scratch, we propose to leverage the speech representations from the pre-trained wav2vec-based XLS-R model. However, the number of parameters of such a model exceeds task-specific DNNs by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00259","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/2210.00259/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":"2210.00259","created_at":"2026-07-05T05:02:30.183459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00259v1","created_at":"2026-07-05T05:02:30.183459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00259","created_at":"2026-07-05T05:02:30.183459+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLPO4AJTGBCF","created_at":"2026-07-05T05:02:30.183459+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLPO4AJTGBCFQREJ","created_at":"2026-07-05T05:02:30.183459+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLPO4AJT","created_at":"2026-07-05T05:02:30.183459+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/XLPO4AJTGBCFQREJUU4CICQIUN","json":"https://pith.science/pith/XLPO4AJTGBCFQREJUU4CICQIUN.json","graph_json":"https://pith.science/api/pith-number/XLPO4AJTGBCFQREJUU4CICQIUN/graph.json","events_json":"https://pith.science/api/pith-number/XLPO4AJTGBCFQREJUU4CICQIUN/events.json","paper":"https://pith.science/paper/XLPO4AJT"},"agent_actions":{"view_html":"https://pith.science/pith/XLPO4AJTGBCFQREJUU4CICQIUN","download_json":"https://pith.science/pith/XLPO4AJTGBCFQREJUU4CICQIUN.json","view_paper":"https://pith.science/paper/XLPO4AJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00259&json=true","fetch_graph":"https://pith.science/api/pith-number/XLPO4AJTGBCFQREJUU4CICQIUN/graph.json","fetch_events":"https://pith.science/api/pith-number/XLPO4AJTGBCFQREJUU4CICQIUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLPO4AJTGBCFQREJUU4CICQIUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLPO4AJTGBCFQREJUU4CICQIUN/action/storage_attestation","attest_author":"https://pith.science/pith/XLPO4AJTGBCFQREJUU4CICQIUN/action/author_attestation","sign_citation":"https://pith.science/pith/XLPO4AJTGBCFQREJUU4CICQIUN/action/citation_signature","submit_replication":"https://pith.science/pith/XLPO4AJTGBCFQREJUU4CICQIUN/action/replication_record"}},"created_at":"2026-07-05T05:02:30.183459+00:00","updated_at":"2026-07-05T05:02:30.183459+00:00"}