Real-Time Streaming Mel Vocoding with Generative Flow Matching

Simon Welker, Tal Peer, Timo Gerkmann
9/18/2025
eess.AScs.LGcs.SD

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

The task of Mel vocoding, i.e., the inversion of a Mel magnitude spectrogram to an audio waveform, is still a key component in many text-to-speech (TTS) systems today. Based on generative flow matching, our prior work on generative STFT phase retrieval (DiffPhase), and the pseudoinverse operator of the Mel filterbank, we develop MelFlow, a streaming-capable generative Mel vocoder for speech sampled at 16 kHz with an algorithmic latency of only 32 ms and a total latency of 48 ms. We show real-time streaming capability at this latency not only in theory, but in practice on a consumer laptop GPU. Furthermore, we show that our model achieves substantially better PESQ and SI-SDR values compared to well-established not streaming-capable baselines for Mel vocoding including HiFi-GAN.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Real-Time Streamable Generative Speech Restoration with Flow Matching

85% match2025

WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching

79% match1 repo1332025

FloWaveNet : A Generative Flow for Raw Audio

79% match1 repo4902018

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

77% match1 repo7132020

PortaSpeech: Portable and High-Quality Generative Text-to-Speech

77% match1 repo1.0k2021

VoXtream: Full-Stream Text-to-Speech with Extremely Low Latency

77% match2025

Cite this paper

@article{welker2025realtime,
  title  = {Real-Time Streaming Mel Vocoding with Generative Flow Matching},
  author = {Simon Welker and Tal Peer and Timo Gerkmann},
  year   = {2025},
  eprint = {2509.15085},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2509.15085v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2509.15085.svg)](https://codeofpaper.com/paper/2509.15085)

Discussion