mlsanityData to 14 Oct 2026

Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance

arXiv 2111.11755 ↗First posted 23 Nov 2021cs.SD cs.AI eess.AScited by 84

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

Abstract (arXiv)

We propose Guided-TTS, a high-quality text-to-speech (TTS) model that does not require any transcript of target speaker using classifier guidance. Guided-TTS combines an unconditional diffusion probabilistic model with a separately trained phoneme classifier for classifier guidance. Our unconditional diffusion model learns to generate speech without any context from untranscribed speech data. For TTS synthesis, we guide the generative process of the diffusion model with a phoneme classifier trained on a large-scale speech recognition dataset. We present a norm-based scaling method that reduces the pronunciation errors of classifier guidance in Guided-TTS. We show that Guided-TTS achieves a performance comparable to that of the state-of-the-art TTS model, Grad-TTS, without any transcript for LJSpeech. We further demonstrate that Guided-TTS performs well on diverse datasets including a long-form untranscribed dataset.

Key facts. Cited by 84 papers in the map (data through 14 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 46 of its 61 references that are in the map. First posted on arXiv 23 Nov 2021.

Builds on

46 of 61 references.

Closest ancestors · 3

Same direction, newest first

  1. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech13 May
  2. 2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speech3 Apr
  3. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesis21 Sep

Other references · 43

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2017Neural Discrete Representation Learningcited by 4,712
  8. 2013Auto-Encoding Variational Bayescited by 4,053
  9. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  10. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  11. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  12. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
31 more
  1. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  2. 2018VoxCeleb2: Deep Speaker Recognitioncited by 875
  3. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  4. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  5. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 717
  6. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  7. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  8. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 490
  9. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 354
  10. 2021Generative Spoken Language Modeling from Raw Audiocited by 340
  11. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 309
  12. 2017Generalized End-to-End Loss for Speaker Verificationcited by 293
  13. 2018Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesiscited by 282
  14. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 273
  15. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 235
  16. 2018Adversarial Audio Synthesiscited by 225
  17. 2018Efficient Neural Audio Synthesiscited by 219
  18. 2017Parallel WaveNet: Fast High-Fidelity Speech Synthesiscited by 215
  19. 2021Text-Free Prosody-Aware Generative Spoken Language Modelingcited by 119
  20. 2018Neural Voice Cloning with a Few Samplescited by 100
  21. 2019High Fidelity Speech Synthesis with Adversarial Networkscited by 92
  22. 2020End-to-End Adversarial Text-to-Speechcited by 77
  23. 2021WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesiscited by 65
  24. 2021Hi-Fi Multi-Speaker English TTS Datasetcited by 60
  25. 2021SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Modelcited by 56
  26. 2018FloWaveNet : A Generative Flow for Raw Audiocited by 54
  27. 2019MelNet: A Generative Model for Audio in the Frequency Domaincited by 42
  28. 2020Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesiscited by 38
  29. 2021AdaSpeech 2: Adaptive Text to Speech with Untranscribed Datacited by 17
  30. 2020Unsupervised Learning For Sequence-to-sequence Text-to-speech For Low-resource Languagescited by 16
  31. 2021VARA-TTS: Non-Autoregressive Text-to-Speech Synthesis based on Very Deep VAE with Residual Attentioncited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 9; 2023: 29; 2024: 31; 2025: 11; 2026: 4.

84 papers.

Sort:

By area:

  1. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
  2. 2022A Survey on Generative Diffusion Modelcited by 240
  3. 2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Modelscited by 236
  4. 2023On Memorization in Diffusion Modelscited by 125
  5. 2022How to Backdoor Diffusion Models?cited by 104
  6. 2023Non-autoregressive Conditional Diffusion Models for Time Series Predictioncited by 78
  7. 2023Diffusion Models for Black-Box Optimizationcited by 76
  8. 2022HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoisingcited by 73
  9. 2024One-Step Diffusion Distillation through Score Implicit Matchingcited by 71
  10. 2023VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Modelscited by 68
  11. 2023Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Biascited by 51
  12. 2024ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reorderingcited by 50
38 more
  1. 2023VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matchingcited by 49
  2. 2025MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesiscited by 41
  3. 2023DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversioncited by 38
  4. 2022EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidancecited by 37
  5. 2023Don't Play Favorites: Minority Guidance for Diffusion Modelscited by 37
  6. 2024Foundation Models for Music: A Surveycited by 37
  7. 2023Multi-Architecture Multi-Expert Diffusion Modelscited by 35
  8. 2023BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inferencecited by 35
  9. 2023HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesiscited by 35
  10. 2022Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Modelscited by 34
  11. 2024DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factorscited by 32
  12. 2023Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shiftcited by 31
  13. 2024Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferencescited by 31
  14. 2023E3 TTS: Easy End-to-End Diffusion-based Text to Speechcited by 30
  15. 2024Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generationcited by 30
  16. 2023Imaginary Voice: Face-styled Diffusion Model for Text-to-Speechcited by 27
  17. 2023Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentationcited by 27
  18. 2024Flow Generator Matchingcited by 26
  19. 2025Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Modelscited by 24
  20. 2024Self-Guidance: Boosting Flow and Diffusion Generation on Their Owncited by 23
  21. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
  22. 2022Towards Practical Plug-and-Play Diffusion Modelscited by 20
  23. 2024DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Datasetcited by 20
  24. 2023Diffusion Models in NLP: A Surveycited by 16
  25. 2024CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversationscited by 15
  26. 2023DiffVoice: Text-to-Speech with Latent Diffusioncited by 13
  27. 2023Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesiscited by 13
  28. 2024CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Modelscited by 13
  29. 2023DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generationcited by 11
  30. 2024DExter: Learning and Controlling Performance Expression with Diffusion Modelscited by 11
  31. 2024VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesiscited by 10
  32. 2022Meta-Learning via Classifier(-free) Diffusion Guidancecited by 9
  33. 2023U-DiT TTS: U-Diffusion Vision Transformer for Text-to-Speechcited by 9
  34. 2023HiddenSinger: High-Quality Singing Voice Synthesis via Neural Audio Codec and Latent Diffusion Modelscited by 9
  35. 2023Synthetic Shifts to Initial Seed Vector Exposes the Brittle Nature of Latent-Based Diffusion Modelscited by 9
  36. 2024Coarse-to-Fine Proposal Refinement Framework for Audio Temporal Forgery Detection and Localizationcited by 9
  37. 2024David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-trainingcited by 9
  38. 2024UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Modelscited by 9

50 most cited of 84 All 84 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Data
  2. 2023Multi-GradSpeech: Towards Diffusion-based Multi-Speaker Text-to-speech Using Consistent Diffusion Models
  3. 2026LLaDA-TTS: Unifying Speech Synthesis and Zero-Shot Editing via Masked Diffusion Modeling
  4. 2026Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech ↗
  5. 2022ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech
  6. 2026DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis
  7. 2025Towards Flow-Matching-based TTS without Classifier-Free Guidance
  8. 2026LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Space