Generative Modeling for Low Dimensional Speech Attributes with Neural Spline Flows
Not on the map. Why?
Abstract (arXiv)
Despite recent advances in generative modeling for text-to-speech synthesis, these models do not yet have the same fine-grained adjustability of pitch-conditioned deterministic models such as FastPitch and FastSpeech2. Pitch information is not only low-dimensional, but also discontinuous, making it particularly difficult to model in a generative setting. Our work explores several techniques for handling the aforementioned issues in the context of Normalizing Flow models. We also find this problem to be very well suited for Neural Spline flows, which is a highly expressive alternative to the more common affine-coupling mechanism in Normalizing Flows.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 32 references that are in the map. First posted on arXiv 3 Mar 2022.
Builds on
18 of 32 references.
References · 18
- 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
- 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
- 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 717
- 2017Masked Autoregressive Flow for Density Estimationcited by 684
- 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
- 2019Neural Spline Flowscited by 596
- 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 447
- 2019Augmented Neural ODEscited by 397
- 2016A Learned Representation For Artistic Stylecited by 341
- 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 273
- 2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speechcited by 157
- 2018Neural Importance Samplingcited by 155
6 more
- 2020FastPitch: Parallel Text-to-speech with Pitch Predictioncited by 151
- 2020SoftFlow: Probabilistic Framework for Normalizing Flow on Manifoldscited by 98
- 2020Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Modelscited by 66
- 2019WaveFlow: A Compact Flow-based Model for Raw Audiocited by 51
- 2019Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokenscited by 44
- 2020VFlow: More Expressive Generative Flows with Variational Data Augmentationcited by 38
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.