Glow-TTS: flow-based synthesis with internal monotonic alignment search

What changed

Used a generative flow and monotonic alignment search to learn text/speech alignment internally for parallel acoustic synthesis without an external teacher aligner.

Scientific scope

Used a generative flow and monotonic alignment search to learn text/speech alignment internally for parallel acoustic synthesis without an external teacher aligner. Inherits flows and monotonic dynamic programming. No external aligner does not mean no alignment assumptions, duration model, phoneme preprocessing or paired data; original comparison is not a general optimal speech-alignment theorem.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits flows and monotonic dynamic programming. No external aligner does not mean no alignment assumptions, duration model, phoneme preprocessing or paired data; original comparison is not a general optimal speech-alignment theorem.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction