mlsanityData to 13 Oct 2026

FlowEdit: Associative Memory for Lifelong Pronunciation Adaptation in Flow-Matching TTS

arXiv 2606.20518 ↗First posted 18 Jun 2026cs.AIcited by 0

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

Flow-matching text-to-speech systems achieve remarkable zero-shot quality but remain static after deployment: pronunciation errors on out-of-vocabulary proper nouns persist unless the model is retrained. We introduce FlowEdit, a life-long adaptation framework for frozen flow-matching TTS that learns pronunciation corrections as latent conditioning edits rather than weight updates. When corrective feedback is provided, FlowEdit optimizes a token-level perturbation in the text embedding space, then stores the correction in a Modern Hopfield Network serving as content-addressable episodic memory. At inference, corrections are retrieved via soft attention with a similarity gate, enabling fuzzy morphological matching. On our curated benchmark of 312 multilingual proper nouns across 18 language families, FlowEdit reduces target-word Phoneme Error Rate by 92.7% relative to the zero-shot baseline while maintaining identical general-speech quality. Corrections complete in approximately 15 seconds on a single GPU.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 24 of its 27 references that are in the map. First posted on arXiv 18 Jun 2026.

Builds on

24 of 27 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Matcha-TTS: A fast TTS architecture with conditional flow matching6 Sep

Other references · 23

  1. 2017Attention Is All You Needcited by 60,106
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,952
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,231
  5. 2022Scalable Diffusion Models with Transformerscited by 5,973
  6. 2022Flow Matching for Generative Modelingcited by 5,542
  7. 2016Overcoming catastrophic forgetting in neural networkscited by 4,753
  8. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,004
  9. 2018Neural Ordinary Differential Equationscited by 3,750
  10. 2022Locating and Editing Factual Associations in GPTcited by 2,650
  11. 2016WaveNet: A Generative Model for Raw Audiocited by 1,717
  12. 2016Progressive Neural Networkscited by 1,347
11 more
  1. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,322
  2. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,148
  3. 2018Experience Replay for Continual Learningcited by 1,082
  4. 2022Mass-Editing Memory in a Transformercited by 990
  5. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 891
  6. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 803
  7. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 745
  8. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 489
  9. 2018CREPE: A Convolutional Representation for Pitch Estimationcited by 110
  10. 2023LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpuscited by 101
  11. 2026SonoEdit: Null-Space Constrained Knowledge Editing for Pronunciation Correction in LLM-Based TTScited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Depth through recurrence: Looped transformers for flow-matching TTS
  2. 2026RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching
  3. 2026Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis
  4. 2026ARCHI-TTS: A flow-matching-based Text-to-Speech Model with Self-supervised Semantic Aligner and Accelerated Inference
  5. 2026Mask, Sample, Revise: A Revisable CTMC Inference Stack for Guided Discrete Flow Matching Text-to-Speech
  6. 2026Transcript-Free Flow-Matching Text-to-Speech via Speech Feature Conditioning
  7. 2026PFluxTTS: Hybrid Flow-Matching TTS with Robust Cross-Lingual Voice Cloning and Inference-Time Model Fusion
  8. 2025ManchuTTS: Towards High-Quality Manchu Speech Synthesis via Flow Matching and Hierarchical Text Representation