mlsanityData to 7 Oct 2026

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

arXiv 2005.11129 ↗First posted 22 May 2020eess.AS cs.SDcited by 269

Not on the map. Why?

Cited by 60 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recently, text-to-speech (TTS) models such as FastSpeech and ParaNet have been proposed to generate mel-spectrograms from text in parallel. Despite the advantage, the parallel TTS models cannot be trained without guidance from autoregressive TTS models as their external aligners. In this work, we propose Glow-TTS, a flow-based generative model for parallel TTS that does not require any external aligner. By combining the properties of flows and dynamic programming, the proposed model searches for the most probable monotonic alignment between text and the latent representation of speech on its own. We demonstrate that enforcing hard monotonic alignments enables robust TTS, which generalizes to long utterances, and employing generative flows enables fast, diverse, and controllable speech synthesis. Glow-TTS obtains an order-of-magnitude speed-up over the autoregressive model, Tacotron 2, at synthesis with comparable speech quality. We further show that our model can be easily extended to a multi-speaker setting.

Key facts. Cited by 269 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 27; 2022: 49; 2023: 65; 2024: 62; 2025: 39; 2026: 27.

269 papers.

Sort:

By area:

  1. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  2. 2022Multimodal Learning with Transformers: A Surveycited by 399
  3. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  4. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 353
  5. 2023AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretrainingcited by 343
  6. 2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 277
  7. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 222
  8. 2021A Survey on Neural Speech Synthesiscited by 182
  9. 2024MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformercited by 159
  10. 2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speechcited by 156
  11. 2021DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanismcited by 154
  12. 2022NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Qualitycited by 151
38 more
  1. 2022ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speechcited by 147
  2. 2023Matcha-TTS: A fast TTS architecture with conditional flow matchingcited by 142
  3. 2022FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesiscited by 136
  4. 2021ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flowscited by 113
  5. 2021AdaSpeech: Adaptive Text to Speech for Custom Voicecited by 98
  6. 2024ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scalecited by 88
  7. 2025IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speechcited by 85
  8. 2021Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidancecited by 84
  9. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
  10. 2023DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Modelscited by 81
  11. 2021PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Priorcited by 78
  12. 2022A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyondcited by 64
  13. 2023Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Biascited by 51
  14. 2024ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reorderingcited by 50
  15. 2023VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matchingcited by 49
  16. 2024Read, Watch and Scream! Sound Generation from Text and Videocited by 48
  17. 2021One TTS Alignment To Rule Them Allcited by 47
  18. 2022DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANscited by 43
  19. 2023WavMark: Watermarking for Audio Generationcited by 41
  20. 2021Neural Dubber: Dubbing for Videos According to Scriptscited by 39
  21. 2025MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesiscited by 39
  22. 2022G2P-DDM: Generating Sign Pose Sequence from Gloss Sequence with Discrete Diffusion Modelcited by 38
  23. 2023DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversioncited by 38
  24. 2022Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Datacited by 35
  25. 2023HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesiscited by 35
  26. 2022Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Modelscited by 34
  27. 2022StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesiscited by 32
  28. 2022BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpuscited by 31
  29. 2024The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audiocited by 31
  30. 2024DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factorscited by 31
  31. 2021Tensor-Train Density Estimationcited by 30
  32. 2023E3 TTS: Easy End-to-End Diffusion-based Text to Speechcited by 30
  33. 2023OpenVoice: Versatile Instant Voice Cloningcited by 30
  34. 2025ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matchingcited by 30
  35. 2023Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesiscited by 29
  36. 2021EdiTTS: Score-based Editing for Controllable Text-to-Speechcited by 28
  37. 2024Diff-RNTraj: A Structure-aware Diffusion Model for Road Network-constrained Trajectory Generationcited by 28
  38. 2022Towards Building Text-To-Speech Systems for the Next Billion Userscited by 27

50 most cited of 269 All 269 (JSON)