{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:D4LZ2WVQJEUM7OY53G3NEYBRGC","short_pith_number":"pith:D4LZ2WVQ","schema_version":"1.0","canonical_sha256":"1f179d5ab04928cfbb1dd9b6d2603130a8b2c984315a34ca02dbe1409d2e10cc","source":{"kind":"arxiv","id":"1510.08484","version":1},"attestation_state":"computed","paper":{"title":"MUSAN: A Music, Speech, and Noise Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Daniel Povey, David Snyder, Guoguo Chen","submitted_at":"2015-10-28T20:59:04Z","abstract_excerpt":"This report introduces a new corpus of music, speech, and noise. This dataset is suitable for training models for voice activity detection (VAD) and music/speech discrimination. Our corpus is released under a flexible Creative Commons license. The dataset consists of music from several genres, speech from twelve languages, and a wide assortment of technical and non-technical noises. We demonstrate use of this corpus for music/speech discrimination on Broadcast news and VAD for speaker identification."},"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":"1510.08484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2015-10-28T20:59:04Z","cross_cats_sorted":[],"title_canon_sha256":"a4fcb4728a3756392bdd2a448b403537288dd6aa5a7b3c1bab17745f774336a5","abstract_canon_sha256":"d7100eef4cdaa6c1243812ab79bb7d4e5b19fb2f2f3014baf8311988338e0387"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:28:28.848156Z","signature_b64":"RoXtPzL+Fo5Qm4gi4SwwDF0X+VRD3FjhMLPxGvUYto06gyAPTA7NeEGa5G9UqlaybvSWz2hIjwvvBkdCoMpiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f179d5ab04928cfbb1dd9b6d2603130a8b2c984315a34ca02dbe1409d2e10cc","last_reissued_at":"2026-05-18T01:28:28.847536Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:28:28.847536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MUSAN: A Music, Speech, and Noise Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Daniel Povey, David Snyder, Guoguo Chen","submitted_at":"2015-10-28T20:59:04Z","abstract_excerpt":"This report introduces a new corpus of music, speech, and noise. This dataset is suitable for training models for voice activity detection (VAD) and music/speech discrimination. Our corpus is released under a flexible Creative Commons license. The dataset consists of music from several genres, speech from twelve languages, and a wide assortment of technical and non-technical noises. We demonstrate use of this corpus for music/speech discrimination on Broadcast news and VAD for speaker identification."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.08484","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":""},"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":"1510.08484","created_at":"2026-05-18T01:28:28.847633+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.08484v1","created_at":"2026-05-18T01:28:28.847633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.08484","created_at":"2026-05-18T01:28:28.847633+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4LZ2WVQJEUM","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4LZ2WVQJEUM7OY5","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4LZ2WVQ","created_at":"2026-05-18T12:29:17.054201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":15,"sample":[{"citing_arxiv_id":"1907.01195","citing_title":"Kite: Automatic speech recognition for unmanned aerial vehicles","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02191","citing_title":"The DKU-SMIIP System for NIST 2018 Speaker Recognition Evaluation","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02194","citing_title":"The DKU System for the Speaker Recognition Task of the 2019 VOiCES from a Distance Challenge","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2401.09512","citing_title":"MLAAD: The Multi-Language Audio Anti-Spoofing Dataset","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2502.20427","citing_title":"DeePen: Penetration Testing for Audio Deepfake Detection","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09568","citing_title":"RADAR Challenge 2026: Robust Audio Deepfake Recognition under Media Transformations","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17443","citing_title":"Analyzing Error Propagation in Korean Spoken QA with ASR-LLM Cascades","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15442","citing_title":"Mind the Gap: Impact of Synthetic Conversational Data on Multi-Talker ASR and Speaker Diarization","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2507.13563","citing_title":"Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2509.16023","citing_title":"Interpreting the Role of Visemes in Audio-Visual Speech Recognition","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2512.16378","citing_title":"Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2602.16416","citing_title":"Online Single-Channel Audio-Based Sound Speed Estimation for Robust Multi-Channel Audio Control","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15044","citing_title":"SpeakerLLM: A Speaker-Specialized Audio-LLM for Speaker Understanding and Verification Reasoning","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.01590","citing_title":"PhiNet: Speaker Verification with Phonetic Interpretability","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03689","citing_title":"MALEFA: Multi-grAnularity Learning and Effective False Alarm Suppression for Zero-shot Keyword Spotting","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12225","citing_title":"Mechanistic Interpretability of ASR models using Sparse Autoencoders","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26465","citing_title":"Diffusion Reconstruction towards Generalizable Audio Deepfake Detection","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26327","citing_title":"Dual-LoRA: Parameter-Efficient Adversarial Disentanglement for Cross-Lingual Speaker Verification","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09568","citing_title":"RADAR Challenge 2026: Robust Audio Deepfake Recognition under Media Transformations","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25624","citing_title":"UNet-Based Fusion and Exponential Moving Average Adaptation for Noise-Robust Speaker Recognition","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21276","citing_title":"Do LLM Decoders Listen Fairly? Benchmarking How Language Model Priors Shape Bias in Speech Recognition","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14806","citing_title":"Listen, Pause, and Reason: Toward Perception-Grounded Hybrid Reasoning for Audio Understanding","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20229","citing_title":"Enhancing Speaker Verification with Whispered Speech via Post-Processing","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4LZ2WVQJEUM7OY53G3NEYBRGC","json":"https://pith.science/pith/D4LZ2WVQJEUM7OY53G3NEYBRGC.json","graph_json":"https://pith.science/api/pith-number/D4LZ2WVQJEUM7OY53G3NEYBRGC/graph.json","events_json":"https://pith.science/api/pith-number/D4LZ2WVQJEUM7OY53G3NEYBRGC/events.json","paper":"https://pith.science/paper/D4LZ2WVQ"},"agent_actions":{"view_html":"https://pith.science/pith/D4LZ2WVQJEUM7OY53G3NEYBRGC","download_json":"https://pith.science/pith/D4LZ2WVQJEUM7OY53G3NEYBRGC.json","view_paper":"https://pith.science/paper/D4LZ2WVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.08484&json=true","fetch_graph":"https://pith.science/api/pith-number/D4LZ2WVQJEUM7OY53G3NEYBRGC/graph.json","fetch_events":"https://pith.science/api/pith-number/D4LZ2WVQJEUM7OY53G3NEYBRGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4LZ2WVQJEUM7OY53G3NEYBRGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4LZ2WVQJEUM7OY53G3NEYBRGC/action/storage_attestation","attest_author":"https://pith.science/pith/D4LZ2WVQJEUM7OY53G3NEYBRGC/action/author_attestation","sign_citation":"https://pith.science/pith/D4LZ2WVQJEUM7OY53G3NEYBRGC/action/citation_signature","submit_replication":"https://pith.science/pith/D4LZ2WVQJEUM7OY53G3NEYBRGC/action/replication_record"}},"created_at":"2026-05-18T01:28:28.847633+00:00","updated_at":"2026-05-18T01:28:28.847633+00:00"}