mlsanityData to 14 Oct 2026

SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech System

arXiv 2503.23108 ↗First posted 29 Mar 2025eess.AS cs.LG cs.SDcited by 2

Not on the map. Why?

Abstract (arXiv)

We introduce SupertonicTTS, a novel text-to-speech (TTS) system designed for efficient and streamlined speech synthesis. SupertonicTTS comprises three components: a speech autoencoder for continuous latent representation, a text-to-latent module leveraging flow-matching for text-to-latent mapping, and an utterance-level duration predictor. To enable a lightweight architecture, we employ a low-dimensional latent space, temporal compression of latents, and ConvNeXt blocks. The TTS pipeline is further simplified by operating directly on raw character-level text and employing cross-attention for text-speech alignment, thus eliminating the need for grapheme-to-phoneme (G2P) modules and external aligners. In addition, we propose context-sharing batch expansion that accelerates loss convergence and stabilizes text-speech alignment with minimal memory and I/O overhead. Experimental results demonstrate that SupertonicTTS delivers performance comparable to contemporary zero-shot TTS models with only 44M parameters, while significantly reducing architectural complexity and computational cost. Audio samples are available at: https://supertonictts.github.io/.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 54 of its 73 references that are in the map. First posted on arXiv 29 Mar 2025.

Builds on

54 of 73 references.

References · 54

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2022Classifier-Free Diffusion Guidancecited by 5,847
  5. 2022Flow Matching for Generative Modelingcited by 5,702
  6. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  7. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  8. 2022A ConvNet for the 2020scited by 3,579
  9. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  10. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  11. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  12. 2021SoundStream: An End-to-End Neural Audio Codeccited by 771
38 more
  1. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
  2. 2022High Fidelity Neural Audio Compressioncited by 687
  3. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 649
  4. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  5. 2021ByT5: Towards a token-free future with pre-trained byte-to-byte modelscited by 509
  6. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 447
  7. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 379
  8. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  9. 2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 278
  10. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 273
  11. 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 251
  12. 2021Speech Resynthesis from Discrete Disentangled Self-Supervised Representationscited by 243
  13. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 226
  14. 2021NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasetscited by 192
  15. 2021SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processingcited by 180
  16. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 179
  17. 2023Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervisioncited by 169
  18. 2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speechcited by 157
  19. 2023Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesiscited by 153
  20. 2024E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTScited by 152
  21. 2024VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wildcited by 120
  22. 2022Latent Diffusion for Language Generationcited by 115
  23. 2018CREPE: A Convolutional Representation for Pitch Estimationcited by 110
  24. 2024The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speechcited by 83
  25. 2021UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generationcited by 74
  26. 2024FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applicationscited by 68
  27. 2024EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberationcited by 64
  28. 2021Hi-Fi Multi-Speaker English TTS Datasetcited by 60
  29. 2017JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesiscited by 58
  30. 2019WaveFlow: A Compact Flow-based Model for Raw Audiocited by 51
  31. 2023Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesiscited by 41
  32. 2022NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesiscited by 38
  33. 2024CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speechcited by 37
  34. 2022Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Datacited by 35
  35. 2024DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factorscited by 32
  36. 2021NeMo Inverse Text Normalization: From Development To Productioncited by 29
  37. 2021EdiTTS: Score-based Editing for Controllable Text-to-Speechcited by 28
  38. 2024SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Modelscited by 23

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matchingcited by 0
  2. 2026Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Modelcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis
  2. 2026FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation
  3. 2026CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents
  4. 2026ARCHI-TTS: A flow-matching-based Text-to-Speech Model with Self-supervised Semantic Aligner and Accelerated Inference
  5. 2026TADA: A Generative Framework for Speech Modeling via Text-Acoustic Dual Alignment
  6. 2024SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models
  7. 2023A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech
  8. 2025GOAT-TTS: Expressive and Realistic Speech Generation via A Dual-Branch LLM