mlsanityData to 14 Oct 2026

Adaptive Oscillatory Inductive Bias for Modeling Sharp Prosodic Dynamics in Diffusion-Based TTS

arXiv 2606.25424 ↗First posted 24 Jun 2026eess.AS cs.AI cs.CLcited by 0

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

Abstract (arXiv)

Diffusion-based text-to-speech (TTS) models have achieved significant improvements in speech quality. However, modeling sharp prosodic transitions and rapid pitch variations in expressive speech remains challenging. Existing diffusion-based TTS decoders commonly utilize periodic nonlinearities such as Snake activation function to capture harmonic structures, but this activation funcation provides limited adaptability when modeling abrupt amplitude and frequency variations. In this paper, we investigate the role of oscillatory inductive bias in diffusion-based TTS decoders and introduce an adaptive oscillatory nonlinearity that enables controllable periodic modulation while maintaining signal stability through a linear bypass component. We refer the resulting TTS system as OscillaTTS. Experiments on the LJSpeech and Emotional Speech Dataset show consistent improvements across objective and subjective evaluations, indicating improved modeling of expressive prosodic dynamics.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 21 of its 25 references that are in the map. First posted on arXiv 24 Jun 2026.

Builds on

21 of 25 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer17 Sep
  2. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models13 Jun
  3. 2023A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI23 Mar
  4. 2021Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance23 Nov
  5. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech13 May
  6. 2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speech3 Apr

Other references · 15

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  2. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 717
  3. 2021Layer-wise Analysis of a Self-supervised Speech Representation Modelcited by 298
  4. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 273
  5. 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 251
  6. 2023Seamless: Multilingual Expressive and Streaming Speech Translationcited by 192
  7. 2021Emotional Voice Conversion: Theory, Databases and ESDcited by 115
  8. 2020An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learningcited by 112
  9. 2020Neural Networks Fail to Learn Periodic Functions and How to Fix Itcited by 100
  10. 2022StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesiscited by 33
  11. 2022iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transformcited by 32
  12. 2023Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictionscited by 23
3 more
  1. 2024Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Surveycited by 23
  2. 2024HOSC: A Periodic Activation Function for Preserving Sharp Features in Implicit Neural Representationscited by 14
  3. 2024VECL-TTS: Voice identity and Emotional style controllable Cross-Lingual Text-to-Speechcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Two-stage Diffusion TTS: Joint Structure and Content Refinement via Jump Diffusion
  2. 2023Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis
  3. 2024Autoregressive Diffusion Transformer for Text-to-Speech Synthesis
  4. 2026Combining Masked Language Modeling and Cross-Modal Contrastive Learning for Prosody-Aware TTS ↗
  5. 2023E3 TTS: Easy End-to-End Diffusion-based Text to Speech
  6. 2026Harmonizing Spectral Evolution in Conditional Flow Matching for TTS
  7. 2024On the Semantic Latent Space of Diffusion-Based Text-to-Speech Models
  8. 2024Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation