{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:P5LFSZZ37Y26XAW7UPNETHDQXR","short_pith_number":"pith:P5LFSZZ3","canonical_record":{"source":{"id":"2407.08551","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T14:36:53Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a17ac2791bdffd09859153d34a1a88c28886d7951ef9f289837f7ec9b9cf78ca","abstract_canon_sha256":"c03dea6507bf8ac024bc38383807f3ff746d098bf1fb5c74e926097cb8ee416b"},"schema_version":"1.0"},"canonical_sha256":"7f5659673bfe35eb82dfa3da499c70bc79e53ce93612836c1b1827643217500a","source":{"kind":"arxiv","id":"2407.08551","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08551","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08551v2","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08551","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"P5LFSZZ37Y26","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"P5LFSZZ37Y26XAW7","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"P5LFSZZ3","created_at":"2026-07-05T11:09:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:P5LFSZZ37Y26XAW7UPNETHDQXR","target":"record","payload":{"canonical_record":{"source":{"id":"2407.08551","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T14:36:53Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a17ac2791bdffd09859153d34a1a88c28886d7951ef9f289837f7ec9b9cf78ca","abstract_canon_sha256":"c03dea6507bf8ac024bc38383807f3ff746d098bf1fb5c74e926097cb8ee416b"},"schema_version":"1.0"},"canonical_sha256":"7f5659673bfe35eb82dfa3da499c70bc79e53ce93612836c1b1827643217500a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:59.871021Z","signature_b64":"SCzZFQqePURVY7X80dYX96lgC1Z//6wuX92FTKDEictVdTgL4/vyeApxPaxYvtKuHLS3bmbztjE+LEXD2I8DBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f5659673bfe35eb82dfa3da499c70bc79e53ce93612836c1b1827643217500a","last_reissued_at":"2026-07-05T11:09:59.870501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:59.870501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.08551","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4ndxtVAy1MjT7EHmoxuV16XGCB8kSiujhfH18TPXrre3mZES4fMZchhh0aCMkQg5YAoNjs2FhA+jQpJiLgU4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:35:08.811459Z"},"content_sha256":"bac09d498bec06dcd4e10a0e1098643868693fc3f09a519c761567f4d48e2d0e","schema_version":"1.0","event_id":"sha256:bac09d498bec06dcd4e10a0e1098643868693fc3f09a519c761567f4d48e2d0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:P5LFSZZ37Y26XAW7UPNETHDQXR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Autoregressive Speech Synthesis without Vector Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bing Han, Furu Wei, Helen Meng, Jinyu Li, Lingwei Meng, Long Zhou, Sanyuan Chen, Sheng Zhao, Shujie Hu, Shujie Liu, Xixin Wu, Yanqing Liu","submitted_at":"2024-07-11T14:36:53Z","abstract_excerpt":"We present MELLE, a novel continuous-valued token based language modeling approach for text-to-speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition, bypassing the need for vector quantization, which is typically designed for audio compression and sacrifices fidelity compared to continuous representations. Specifically, (i) instead of cross-entropy loss, we apply regression loss with a proposed spectrogram flux loss function to model the probability distribution of the continuous-valued tokens; (ii) we have incorporated variatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08551","kind":"arxiv","version":2},"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/2407.08551/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gjf/cFpL9LgerUrQ2xh0PrIuuiMbsdrL3h7riWxoaybUHdCFVxFboAkoJOAobIer4mRgbkOplMQfR0PeMqJRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:35:08.812247Z"},"content_sha256":"eb68bf260ced176318bf2557f3dda5c5e4fe34908a1b2941d5beeb1140c10ec4","schema_version":"1.0","event_id":"sha256:eb68bf260ced176318bf2557f3dda5c5e4fe34908a1b2941d5beeb1140c10ec4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P5LFSZZ37Y26XAW7UPNETHDQXR/bundle.json","state_url":"https://pith.science/pith/P5LFSZZ37Y26XAW7UPNETHDQXR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P5LFSZZ37Y26XAW7UPNETHDQXR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T20:35:08Z","links":{"resolver":"https://pith.science/pith/P5LFSZZ37Y26XAW7UPNETHDQXR","bundle":"https://pith.science/pith/P5LFSZZ37Y26XAW7UPNETHDQXR/bundle.json","state":"https://pith.science/pith/P5LFSZZ37Y26XAW7UPNETHDQXR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P5LFSZZ37Y26XAW7UPNETHDQXR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P5LFSZZ37Y26XAW7UPNETHDQXR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c03dea6507bf8ac024bc38383807f3ff746d098bf1fb5c74e926097cb8ee416b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T14:36:53Z","title_canon_sha256":"a17ac2791bdffd09859153d34a1a88c28886d7951ef9f289837f7ec9b9cf78ca"},"schema_version":"1.0","source":{"id":"2407.08551","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08551","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08551v2","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08551","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"P5LFSZZ37Y26","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"P5LFSZZ37Y26XAW7","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"P5LFSZZ3","created_at":"2026-07-05T11:09:59Z"}],"graph_snapshots":[{"event_id":"sha256:eb68bf260ced176318bf2557f3dda5c5e4fe34908a1b2941d5beeb1140c10ec4","target":"graph","created_at":"2026-07-05T11:09:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.08551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present MELLE, a novel continuous-valued token based language modeling approach for text-to-speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition, bypassing the need for vector quantization, which is typically designed for audio compression and sacrifices fidelity compared to continuous representations. Specifically, (i) instead of cross-entropy loss, we apply regression loss with a proposed spectrogram flux loss function to model the probability distribution of the continuous-valued tokens; (ii) we have incorporated variatio","authors_text":"Bing Han, Furu Wei, Helen Meng, Jinyu Li, Lingwei Meng, Long Zhou, Sanyuan Chen, Sheng Zhao, Shujie Hu, Shujie Liu, Xixin Wu, Yanqing Liu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T14:36:53Z","title":"Autoregressive Speech Synthesis without Vector Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08551","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bac09d498bec06dcd4e10a0e1098643868693fc3f09a519c761567f4d48e2d0e","target":"record","created_at":"2026-07-05T11:09:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c03dea6507bf8ac024bc38383807f3ff746d098bf1fb5c74e926097cb8ee416b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T14:36:53Z","title_canon_sha256":"a17ac2791bdffd09859153d34a1a88c28886d7951ef9f289837f7ec9b9cf78ca"},"schema_version":"1.0","source":{"id":"2407.08551","kind":"arxiv","version":2}},"canonical_sha256":"7f5659673bfe35eb82dfa3da499c70bc79e53ce93612836c1b1827643217500a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f5659673bfe35eb82dfa3da499c70bc79e53ce93612836c1b1827643217500a","first_computed_at":"2026-07-05T11:09:59.870501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:59.870501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SCzZFQqePURVY7X80dYX96lgC1Z//6wuX92FTKDEictVdTgL4/vyeApxPaxYvtKuHLS3bmbztjE+LEXD2I8DBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:59.871021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08551","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bac09d498bec06dcd4e10a0e1098643868693fc3f09a519c761567f4d48e2d0e","sha256:eb68bf260ced176318bf2557f3dda5c5e4fe34908a1b2941d5beeb1140c10ec4"],"state_sha256":"0ca1af1840c85080b05cedee4db6d335b9cbb0bbd31a05fa18b60e2056de6f52"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/rY6DDGO9lpcmvgoBfh8TCer946hAt3j0AM6R1i+3/Tg9swQpwMcNQ2Id/NSTSnfksYAPLf5tyuD2eYFpQGADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:35:08.818019Z","bundle_sha256":"4c6bcbb8e84ca6c620b357f174c3a4a0bac4726315cef4aedfb6d3c5c1331794"}}