# Audio, speech and music

Area: [Diffusion models](https://mlsanity.com/diffusion/index.md). HTML: https://mlsanity.com/diffusion/audio-speech-and-music/

## Key facts

- Audio, speech and music: 891 papers on arXiv since 2020 (data through 14 Oct 2026).
- 188 of its 891 mapped papers (21%) cite “DiffWave: A Versatile Diffusion Model for Audio Synthesis” (2020, arXiv 2009.09761).
- 167 of its 891 mapped papers (19%) cite “AudioLDM: Text-to-Audio Generation with Latent Diffusion Models” (2023, arXiv 2301.12503).
- 26 new papers 17 Sep–14 Oct.

## Most cited here

- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020), cited by 188 papers here
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023), cited by 167 papers here
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023), cited by 128 papers here
- [Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech](https://mlsanity.com/paper/2105.06337/) (2021), cited by 118 papers here
- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022), cited by 102 papers here
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024), cited by 99 papers here
- [Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models](https://mlsanity.com/paper/2301.12661/) (2023), cited by 91 papers here
- [Conditional Diffusion Probabilistic Model for Speech Enhancement](https://mlsanity.com/paper/2202.05256/) (2022), cited by 78 papers here
- [Diffsound: Discrete Diffusion Model for Text-to-sound Generation](https://mlsanity.com/paper/2207.09983/) (2022), cited by 77 papers here
- [NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers](https://mlsanity.com/paper/2304.09116/) (2023), cited by 69 papers here

## New (17 Sep–14 Oct)

- [Revise-TTS: A Non-Masking Refinement Framework for Masked Diffusion Models in Text-to-Speech](https://mlsanity.com/paper/2610.19499/) (2026-10-14)
- [Full-duplex Spoken Language Modeling with Discrete Diffusion](https://mlsanity.com/paper/2610.17780/) (2026-10-13)
- [Self-Representation Alignment in Diffusion Models for Video Background Music Generation](https://mlsanity.com/paper/2610.15575/) (2026-10-11)
- [AlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned Generation](https://mlsanity.com/paper/2610.14697/) (2026-10-10)
- [AV-FlowEdit: Training-Free Prompt-Driven Audio-Visual Editing with Event-Aware Spectral Trajectory Preservation](https://mlsanity.com/paper/2610.13072/) (2026-10-09)
- [DiffuPlex: Accelerating Full-Duplex Spoken Dialog Models via Rolling Masked Diffusion](https://mlsanity.com/paper/2610.12214/) (2026-10-08)
- [Real-Time Joint Audio-Video Generation by Parallel Adapter Composition](https://mlsanity.com/paper/2610.10343/) (2026-10-07)
- [Smorph: Playable Sound Morphing with Diffusion Models](https://mlsanity.com/paper/2610.06478/) (2026-10-05)
- [Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation](https://mlsanity.com/paper/2610.05608/) (2026-10-04)
- [DriftTTS: Few-Step Text-to-Speech Without Distillation via Distribution-Matching Drift](https://mlsanity.com/paper/2610.03390/) (2026-10-02)
- [NEUROTOKEN: Joint Source and Directional AAD with Envelope Decoding via Conditional Flow Matching](https://mlsanity.com/paper/2610.00397/) (2026-09-30)
- [MeanVoiceFlow2: Joint Optimization of Mean Flow and Content Encoder for Fast One-Step Zero-Shot Voice Conversion](https://mlsanity.com/paper/2609.40087/) (2026-09-30)
- [ECHO-G: Embodied Co-speech Humanoid mOtion Generation](https://mlsanity.com/paper/2609.39575/) (2026-09-30)
- [Harmonizing Spectral Evolution in Conditional Flow Matching for TTS](https://mlsanity.com/paper/2609.34431/) (2026-09-30)
- [JoyAI-Voice 2.0: A Full-Continuous Autoregressive Speech Generation Model with Semantic-Acoustic Joint Representation](https://mlsanity.com/paper/2610.08834/) (2026-09-29)
- [Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL](https://mlsanity.com/paper/2609.37200/) (2026-09-29)
- [Distill Locally, Schedule Globally: Flow Maps for Few-Step Text-to-Speech](https://mlsanity.com/paper/2609.36324/) (2026-09-28)
- [SEmoEdit: Probing and Harnessing the Editability of Pre-trained Speech Flows](https://mlsanity.com/paper/2609.34648/) (2026-09-28)
- [NVAlign: Direct-Gradient Optimization for Non-Verbal Control in Continuous Autoregressive Flow Matching Text-to-Speech](https://mlsanity.com/paper/2609.31892/) (2026-09-25)
- [Depth through recurrence: Looped transformers for flow-matching TTS](https://mlsanity.com/paper/2609.29768/) (2026-09-24)
- [Off-manifold robustness in synthesizer inversion with joint distribution flow matching](https://mlsanity.com/paper/2609.29320/) (2026-09-24)
- [ReaFlow-TTS: Realization-Conditioned Flow Matching for High-Quality and Controllable Speech Synthesis](https://mlsanity.com/paper/2609.28906/) (2026-09-24)
- [UNITE-AUDIO: Joint Learning of Continuous Tokenization and Latent Flow Matching for Text-to-Audio Generation](https://mlsanity.com/paper/2609.28206/) (2026-09-23)
- [P2Flow: Phoneme-aware Progressive Flow Matching for Extreme Speech Super-Resolution](https://mlsanity.com/paper/2609.24138/) (2026-09-21)
- [Generative Learning for Ambisonic Upscaling](https://mlsanity.com/paper/2609.23479/) (2026-09-20)
- [DiffVQE2: An Efficient Low-delay Diffusion Model for Acoustic Echo and Noise Control](https://mlsanity.com/paper/2609.31703/) (2026-09-19)