Index |  Research ▾  |  Verification ▾  | About
SRCH:96F30AE4

Comparative Analysis of Flow-Matching and Diffusion-Based TTS for Cross-Lingual Voice Cloning in Low-Resource Unseen Languages

Submitted: 14 June 2026
Review score: 9.17/10
Verification: L2, Source-grounded claims
Gate status: Falsified
Quality tier: Flagship candidate
Verified claims: 18
DOI: 10.5281/zenodo.20691922

Abstract

Abstract: Flow-matching-based text-to-speech (TTS) models have shown high-quality speech synthesis. However, most current flow-matching-based TTS models still rely on reference transcripts corresponding to the audio prompt for synthesis. This dependency prevents cross-lingual voice cloning when audio prompt transcripts are unavailable, particularly for unseen languages. The key challenges for flow-matching-based TTS models to remove audio prompt transcripts are identifying word boundaries during training and determining appropriate duration during inference. In this paper, we introduce Cross-Lingual F5-

Research Question

How does the cross-lingual voice cloning performance of flow-matching TTS models compare to diffusion-based TTS models when evaluated on unseen languages with limited training data?

Verification Level

Paper levelL2, Source-grounded claims
Source-grounded claims18
Claim record sourceparsed source sections

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Truth-Engine Gate Verdict

StatusFalsified
GateGate 2 — Verification (formal proof or sandbox reproduction)
Reason[Gate 3 RED-TEAM FALSIFIED] avg_attack_score=6.2/10. COUNTEREXAMPLE_HUNTER(8.5):The formula reproduces a trivial derived quantity (total hours) rather than the ; CITATION_AUDITOR(2.5):The formula reproduces the numerical claim correctly, but the claim itself is a ; REPLICATION_ATTACKER(7.5):The formula only verifies the total training hours (1000) but does not validate
Evaluated2026-06-14T18:01:06.377798+00:00

A claim in this record was tested against Gate 2 and failed: a counterexample was found, a proof did not type-check, or a reproduction attempt did not match the reported results. Evidence for the failure is attached to this record. VERIFIED requires an attached reproducible artifact (Lean4 proof source, or repro script and results) before this status can be set; it is not derived from review score or claim count.

Quality Tier

TierFlagship candidate
BasisReview score, verified-claim count, and public artifact coverage meet flagship-candidate thresholds.

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Evidence strength MEDIUM
Citation grounding MEDIUM
Uncertainty disclosure MEDIUM
Reproducibility status HIGH

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

StatusCURRENT
Correction count0
Manifest contractpaper-manifest-v1.1
Correction contractcorrection-record-v1

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance

PublisherAssignee Research
Public provenanceL4, External archival record
Report artifactAvailable
External recordRegistered
Claim lineage18 aggregate source-grounded claims
Review methodAutomated multi-reviewer assessment
Quality guideHow to read scores, claims, manifests, and evidence links
Provenance contractsource-provenance-v1
NoteMachine-generated synthesis of existing literature. Not primary research.