mlsanityData to 14 Oct 2026

SlimSpeech: Lightweight and Efficient Text-to-Speech with Slim Rectified Flow

arXiv 2504.07776 ↗First posted 10 Apr 2025cs.SD cs.AIcited by 3

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

Abstract (arXiv)

Recently, flow matching based speech synthesis has significantly enhanced the quality of synthesized speech while reducing the number of inference steps. In this paper, we introduce SlimSpeech, a lightweight and efficient speech synthesis system based on rectified flow. We have built upon the existing speech synthesis method utilizing the rectified flow model, modifying its structure to reduce parameters and serve as a teacher model. By refining the reflow operation, we directly derive a smaller model with a more straight sampling trajectory from the larger model, while utilizing distillation techniques to further enhance the model performance. Experimental results demonstrate that our proposed method, with significantly reduced model parameters, achieves comparable performance to larger models through one-step sampling.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 25 of its 30 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

25 of 30 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation12 Jun
  2. 2023ReFlow-TTS: A Rectified Flow Model for High-fidelity Text-to-Speech29 Sep
  3. 2023VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching10 Sep
  4. 2023Matcha-TTS: A fast TTS architecture with conditional flow matching6 Sep
  5. 2023LightGrad: Lightweight Diffusion Probabilistic Model for Text-to-Speech31 Aug
  6. 2023CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model11 May
  7. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Models29 Jan
  8. 2022ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech13 Jul
  9. 2022DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs28 Jan
  10. 2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speech3 Apr
  11. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesis21 Sep

Other references · 14

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2022Flow Matching for Generative Modelingcited by 5,702
  6. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  7. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  8. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  9. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  10. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 717
  11. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 516
  12. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 379
2 more
  1. 2024SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flowcited by 30
  2. 2023Interpretable Style Transfer for Text-to-Speech with ControlVAE and Diffusion Bridgecited by 3

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matchingcited by 30
  2. 2025Discl-VC: Disentangled Discrete Tokens and In-Context Learning for Controllable Zero-Shot Voice Conversioncited by 5
  3. 2025ManchuTTS: Towards High-Quality Manchu Speech Synthesis via Flow Matching and Hierarchical Text Representationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matching
  2. 2025Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling
  3. 2026DSFlow: Dual Supervision and Step-Aware Architecture for One-Step Flow Matching Speech Synthesis
  4. 2025Shallow Flow Matching for Coarse-to-Fine Text-to-Speech Synthesis
  5. 2022Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform
  6. 2026Staged Depth-Pruning Distillation of a Flow-Matching Text-to-Speech Teacher: A Compact Hindi Speech Synthesizer
  7. 2025Towards Flow-Matching-based TTS without Classifier-Free Guidance
  8. 2026ReaFlow-TTS: Realization-Conditioned Flow Matching for High-Quality and Controllable Speech Synthesis