{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IURHYSVM22PPLS3KVX6PQKNTMJ","short_pith_number":"pith:IURHYSVM","schema_version":"1.0","canonical_sha256":"45227c4aacd69ef5cb6aadfcf829b362789c3875bf3d7f566ef1fda7e565a6b9","source":{"kind":"arxiv","id":"2106.15649","version":1},"attestation_state":"computed","paper":{"title":"Multi-Scale Spectrogram Modelling for Neural Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexis Moinet, Ammar Abbas, Arnaud Joly, Bajibabu Bollepalli, Penny Karanasou, Peter Makarov, Simon Slangens, Sri Karlapati, Thomas Drugman","submitted_at":"2021-06-29T18:01:34Z","abstract_excerpt":"We propose a novel Multi-Scale Spectrogram (MSS) modelling approach to synthesise speech with an improved coarse and fine-grained prosody. We present a generic multi-scale spectrogram prediction mechanism where the system first predicts coarser scale mel-spectrograms that capture the suprasegmental information in speech, and later uses these coarser scale mel-spectrograms to predict finer scale mel-spectrograms capturing fine-grained prosody.\n  We present details for two specific versions of MSS called Word-level MSS and Sentence-level MSS where the scales in our system are motivated by the li"},"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":"2106.15649","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-29T18:01:34Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"02a45558559c7d13dd90bf841ed357c68022536b164aad8298606fbe8ae1934a","abstract_canon_sha256":"5070105fa53bfbc06f492549a470a75368416fef0b2f0dbb0d644a3ffeda7749"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:53:58.952188Z","signature_b64":"oLfte02AxnxgsxbnL2Sq0b3DpopV/UQPiYmwjil43JdWpz0cT/Bt7oiX29eAd+coQ8eqymkhJijaCvRXKF9YCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45227c4aacd69ef5cb6aadfcf829b362789c3875bf3d7f566ef1fda7e565a6b9","last_reissued_at":"2026-07-05T02:53:58.951745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:53:58.951745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Scale Spectrogram Modelling for Neural Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexis Moinet, Ammar Abbas, Arnaud Joly, Bajibabu Bollepalli, Penny Karanasou, Peter Makarov, Simon Slangens, Sri Karlapati, Thomas Drugman","submitted_at":"2021-06-29T18:01:34Z","abstract_excerpt":"We propose a novel Multi-Scale Spectrogram (MSS) modelling approach to synthesise speech with an improved coarse and fine-grained prosody. We present a generic multi-scale spectrogram prediction mechanism where the system first predicts coarser scale mel-spectrograms that capture the suprasegmental information in speech, and later uses these coarser scale mel-spectrograms to predict finer scale mel-spectrograms capturing fine-grained prosody.\n  We present details for two specific versions of MSS called Word-level MSS and Sentence-level MSS where the scales in our system are motivated by the li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15649","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/2106.15649/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":"2106.15649","created_at":"2026-07-05T02:53:58.951799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.15649v1","created_at":"2026-07-05T02:53:58.951799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15649","created_at":"2026-07-05T02:53:58.951799+00:00"},{"alias_kind":"pith_short_12","alias_value":"IURHYSVM22PP","created_at":"2026-07-05T02:53:58.951799+00:00"},{"alias_kind":"pith_short_16","alias_value":"IURHYSVM22PPLS3K","created_at":"2026-07-05T02:53:58.951799+00:00"},{"alias_kind":"pith_short_8","alias_value":"IURHYSVM","created_at":"2026-07-05T02:53:58.951799+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/IURHYSVM22PPLS3KVX6PQKNTMJ","json":"https://pith.science/pith/IURHYSVM22PPLS3KVX6PQKNTMJ.json","graph_json":"https://pith.science/api/pith-number/IURHYSVM22PPLS3KVX6PQKNTMJ/graph.json","events_json":"https://pith.science/api/pith-number/IURHYSVM22PPLS3KVX6PQKNTMJ/events.json","paper":"https://pith.science/paper/IURHYSVM"},"agent_actions":{"view_html":"https://pith.science/pith/IURHYSVM22PPLS3KVX6PQKNTMJ","download_json":"https://pith.science/pith/IURHYSVM22PPLS3KVX6PQKNTMJ.json","view_paper":"https://pith.science/paper/IURHYSVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.15649&json=true","fetch_graph":"https://pith.science/api/pith-number/IURHYSVM22PPLS3KVX6PQKNTMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/IURHYSVM22PPLS3KVX6PQKNTMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IURHYSVM22PPLS3KVX6PQKNTMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IURHYSVM22PPLS3KVX6PQKNTMJ/action/storage_attestation","attest_author":"https://pith.science/pith/IURHYSVM22PPLS3KVX6PQKNTMJ/action/author_attestation","sign_citation":"https://pith.science/pith/IURHYSVM22PPLS3KVX6PQKNTMJ/action/citation_signature","submit_replication":"https://pith.science/pith/IURHYSVM22PPLS3KVX6PQKNTMJ/action/replication_record"}},"created_at":"2026-07-05T02:53:58.951799+00:00","updated_at":"2026-07-05T02:53:58.951799+00:00"}