</> Code with Papers by Syntology

Papers › OverFlow: Putting flows on top of neural transducers for better TTS

OverFlow: Putting flows on top of neural transducers for better TTS

13 Nov 2022arXiv:2211.06892archive 2025-07-28

Shivam Mehta, Ambika Kirkland, Harm Lameris, Jonas Beskow, Éva Székely, Gustav Eje Henter

Neural HMMs are a type of neural transducer recently proposed for sequence-to-sequence modelling in text-to-speech. They combine the best features of classic statistical speech synthesis and modern neural TTS, requiring less data and fewer training updates, and are less prone to gibberish output caused by neural attention failures. In this paper, we combine neural HMM TTS with normalising flows for describing the highly non-Gaussian distribution of speech acoustics. The result is a powerful, fully probabilistic model of durations and acoustics that can be trained using exact maximum likelihood. Experiments show that a system based on our proposal needs fewer updates than comparable methods to produce accurate pronunciations and a subjective speech quality close to natural speech. Please see https://shivammehta25.github.io/OverFlow/ for audio examples and code.

PaperPDFCode

Code

coqui-ai/TTS officialmentioned in papermentioned on GitHubpytorchMPL-2.0 report
shivammehta25/OverFlow officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Normalising FlowsSpeech SynthesisText to SpeechText-To-Speech Synthesistext-to-speech

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-To-Speech Synthesis LJSpeech OverFlow Audio Quality MOS 3.37 #11 of 16 Archive leaderboard report
Text-To-Speech Synthesis LJSpeech OverFlow Word Error Rate (WER) 2.30 #11 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections