mlsanityData to 13 Oct 2026

OverFlow: Putting flows on top of neural transducers for better TTS

arXiv 2211.06892 ↗First posted 13 Nov 2022eess.AS cs.HC cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Neural HMMs are a type of neural transducer recently proposed for sequence-to-sequence modelling in text-to-speech. They combine the best features of classic statistical speech synthesis and modern neural TTS, requiring less data and fewer training updates, and are less prone to gibberish output caused by neural attention failures. In this paper, we combine neural HMM TTS with normalising flows for describing the highly non-Gaussian distribution of speech acoustics. The result is a powerful, fully probabilistic model of durations and acoustics that can be trained using exact maximum likelihood. Experiments show that a system based on our proposal needs fewer updates than comparable methods to produce accurate pronunciations and a subjective speech quality close to natural speech. Please see https://shivammehta25.github.io/OverFlow/ for audio examples and code.

Key facts. Cited by 8 papers in the map (data through 13 Oct 2026). Builds on 24 of its 44 references that are in the map. First posted on arXiv 13 Nov 2022.

Builds on

24 of 44 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,106
  2. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,542
  3. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,317
  4. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,148
  5. 2021Variational Diffusion Modelscited by 1,148
  6. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 803
  7. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 559
  8. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 489
  9. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 446
  10. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 309
  11. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 272
  12. 2018Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesiscited by 259
12 more
  1. 2020Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognitioncited by 185
  2. 2020FastPitch: Parallel Text-to-speech with Pitch Predictioncited by 151
  3. 2020Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesiscited by 54
  4. 2021One TTS Alignment To Rule Them Allcited by 47
  5. 2019Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTScited by 33
  6. 2016Unsupervised Neural Hidden Markov Modelscited by 19
  7. 2016Online Segment to Segment Neural Transductioncited by 14
  8. 2020EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecturecited by 14
  9. 2021Neural HMMs are all you need (for high-quality attention-free TTS)cited by 8
  10. 2021Robust Classification using Hidden Markov Models and Mixtures of Normalizing Flowscited by 4
  11. 2021Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainabilitycited by 4
  12. 2016Median-Based Generation of Synthetic Speech Durations using a Non-Parametric Approachcited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 4; 2024: 2; 2025: 1; 2026: 1.

8 papers.

  1. 2023Matcha-TTS: A fast TTS architecture with conditional flow matchingcited by 144
  2. 2025TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modelingcited by 15
  3. 2023Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesiscited by 13
  4. 2023Unified speech and gesture synthesis using flow matchingcited by 6
  5. 2024Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesiscited by 5
  6. 2024A Language Modeling Approach to Diacritic-Free Hebrew TTScited by 2
  7. 2023Comparative Analysis of Transfer Learning in Deep Learning Text-to-Speech Models on a Few-Shot, Low-Resource, Customized Datasetcited by 1
  8. 2026Scene-aware Prediction of Diverse Human Movement Goalscited by 0