{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MICOZFFBN2SQTKNJEJRYGGW5PB","short_pith_number":"pith:MICOZFFB","schema_version":"1.0","canonical_sha256":"6204ec94a16ea509a9a92263831add7878f53cc8e1c8521b8926a266eb326590","source":{"kind":"arxiv","id":"2304.01448","version":1},"attestation_state":"computed","paper":{"title":"TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Anurag Kumar, Buye Xu, Ethan Henderson, Ke Tan, Pranay Manocha, Xiaohui Zhang, Zhaoheng Ni","submitted_at":"2023-04-04T01:44:24Z","abstract_excerpt":"Measuring quality and intelligibility of a speech signal is usually a critical step in development of speech processing systems. To enable this, a variety of metrics to measure quality and intelligibility under different assumptions have been developed. Through this paper, we introduce tools and a set of models to estimate such known metrics using deep neural networks. These models are made available in the well-established TorchAudio library, the core audio and speech processing library within the PyTorch deep learning framework. We refer to it as TorchAudio-Squim, TorchAudio-Speech QUality a"},"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":"2304.01448","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-04-04T01:44:24Z","cross_cats_sorted":[],"title_canon_sha256":"8fb814246c55dd9d0834669120b7c9908c9f738a958f11443150576e648ce5da","abstract_canon_sha256":"8d0b92ea2c15c2f1cac18ea04b5c08d7e3812bbf5a18bf3a48d95215077bb2e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:40.622050Z","signature_b64":"nXz/SmdLC17KXqax44ZfzsLb1A79/1MEx0fh2JDvvqEgIE3c5rzmfwnikzj2TFovFZ7jgXpa8mpJrDowwqt0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6204ec94a16ea509a9a92263831add7878f53cc8e1c8521b8926a266eb326590","last_reissued_at":"2026-07-05T05:57:40.621615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:40.621615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Anurag Kumar, Buye Xu, Ethan Henderson, Ke Tan, Pranay Manocha, Xiaohui Zhang, Zhaoheng Ni","submitted_at":"2023-04-04T01:44:24Z","abstract_excerpt":"Measuring quality and intelligibility of a speech signal is usually a critical step in development of speech processing systems. To enable this, a variety of metrics to measure quality and intelligibility under different assumptions have been developed. Through this paper, we introduce tools and a set of models to estimate such known metrics using deep neural networks. These models are made available in the well-established TorchAudio library, the core audio and speech processing library within the PyTorch deep learning framework. We refer to it as TorchAudio-Squim, TorchAudio-Speech QUality a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01448","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/2304.01448/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":"2304.01448","created_at":"2026-07-05T05:57:40.621681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.01448v1","created_at":"2026-07-05T05:57:40.621681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01448","created_at":"2026-07-05T05:57:40.621681+00:00"},{"alias_kind":"pith_short_12","alias_value":"MICOZFFBN2SQ","created_at":"2026-07-05T05:57:40.621681+00:00"},{"alias_kind":"pith_short_16","alias_value":"MICOZFFBN2SQTKNJ","created_at":"2026-07-05T05:57:40.621681+00:00"},{"alias_kind":"pith_short_8","alias_value":"MICOZFFB","created_at":"2026-07-05T05:57:40.621681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02244","citing_title":"Spectrogram Patch Codec: A 2D Block-Quantized VQ-VAE and HiFi-GAN for Neural Speech Coding","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MICOZFFBN2SQTKNJEJRYGGW5PB","json":"https://pith.science/pith/MICOZFFBN2SQTKNJEJRYGGW5PB.json","graph_json":"https://pith.science/api/pith-number/MICOZFFBN2SQTKNJEJRYGGW5PB/graph.json","events_json":"https://pith.science/api/pith-number/MICOZFFBN2SQTKNJEJRYGGW5PB/events.json","paper":"https://pith.science/paper/MICOZFFB"},"agent_actions":{"view_html":"https://pith.science/pith/MICOZFFBN2SQTKNJEJRYGGW5PB","download_json":"https://pith.science/pith/MICOZFFBN2SQTKNJEJRYGGW5PB.json","view_paper":"https://pith.science/paper/MICOZFFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.01448&json=true","fetch_graph":"https://pith.science/api/pith-number/MICOZFFBN2SQTKNJEJRYGGW5PB/graph.json","fetch_events":"https://pith.science/api/pith-number/MICOZFFBN2SQTKNJEJRYGGW5PB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MICOZFFBN2SQTKNJEJRYGGW5PB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MICOZFFBN2SQTKNJEJRYGGW5PB/action/storage_attestation","attest_author":"https://pith.science/pith/MICOZFFBN2SQTKNJEJRYGGW5PB/action/author_attestation","sign_citation":"https://pith.science/pith/MICOZFFBN2SQTKNJEJRYGGW5PB/action/citation_signature","submit_replication":"https://pith.science/pith/MICOZFFBN2SQTKNJEJRYGGW5PB/action/replication_record"}},"created_at":"2026-07-05T05:57:40.621681+00:00","updated_at":"2026-07-05T05:57:40.621681+00:00"}