audio_gen.md

Audio Gen

• Audio Gen
  • Survey
  • Audio Generation
  • Speech Generation
  • Conversion
  • Audio Editting
  • Datasets
  • Toolkits
  • Products
  • Misc

Survey

• awesome-voice-conversion - JeffC0628

Audio Generation

• Fast Text-to-Audio Generation with Adversarial Post-Training, arXiv, 2505.08175, arxiv, pdf, cication: -1

  Zachary Novack, Zach Evans, Zack Zukowski, ..., Taylor Berg-Kirkpatrick, Jordi Pons · (huggingface) · (arc-text2audio.github)

• AudioX: Diffusion Transformer for Anything-to-Audio Generation, arXiv, 2503.10522, arxiv, pdf, cication: -1

  Zeyue Tian, Yizhu Jin, Zhaoyang Liu, ..., Wei Xue, Yike Guo · (zeyuet.github)

• TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization, arXiv, 2412.21037, arxiv, pdf, cication: -1

  Chia-Yu Hung, Navonil Majumder, Zhifeng Kong, ..., Bryan Catanzaro, Soujanya Poria · (tangoflux.github)

• Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks, icassp 2024-2024 ieee international conference on acoustics …, 2024, arxiv, pdf, cication: -1

  Soumi Maiti, Yifan Peng, Shukjae Choi, ..., Xuankai Chang, Shinji Watanabe

• Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis, arXiv, 2412.15322, arxiv, pdf, cication: -1

  Ho Kei Cheng, Masato Ishii, Akio Hayakawa, ..., Alexander Schwing, Yuki Mitsufuji · (huggingface) · (hkchengrex) · (MMAudio - hkchengrex)

• Fugatto is a framework for audio synthesis and transformation given text instructions and optional audio inputs.

  · (fugatto.github)

• Tell What You Hear From What You See -- Video to Audio Generation Through Text, arXiv, 2411.05679, arxiv, pdf, cication: -1

  Xiulong Liu, Kun Su, Eli Shlizerman

• Audiobox TTA-RAG: Improving Zero-Shot and Few-Shot Text-To-Audio with Retrieval-Augmented Generation, arXiv, 2411.05141, arxiv, pdf, cication: -1

  Mu Yang, Bowen Shi, Matthew Le, ..., Wei-Ning Hsu, Andros Tjandra

• FlashAudio: Rectified Flows for Fast and High-Fidelity Text-to-Audio Generation, arXiv, 2410.12266, arxiv, pdf, cication: -1

  Huadai Liu, Jialei Wang, Rongjie Huang, ..., Wei Xue, Zhou Zhao

• Movie Gen: A Cast of Media Foundation Models, arXiv, 2410.13720, arxiv, pdf, cication: -1

  Adam Polyak, Amit Zohar, Andrew Brown, ..., Vladan Petrovic, Yuming Du · (ai.meta)

Speech Generation

• WavReward: Spoken Dialogue Models With Generalist Reward Evaluators, arXiv, 2505.09558, arxiv, pdf, cication: -1

  Shengpeng Ji, Tianle Liang, Yangzhuo Li, ..., Junyang Lin, Zhou Zhao

• Metis: A Foundation Speech Generation Model with Masked Generative Pre-training

• Recent Advances in Discrete Speech Tokens: A Review, arXiv, 2502.06490, arxiv, pdf, cication: -1

  Yiwei Guo, Zhihan Li, Hankun Wang, ..., Shujie Liu, Kai Yu

• Introducing hertz-dev, the first open-source base model for conversational audio generation

  · (x) · (hertz-dev - Standard-Intelligence)

Conversion

• CoDiff-VC: A Codec-Assisted Diffusion Model for Zero-shot Voice Conversion, arXiv, 2411.18918, arxiv, pdf, cication: -1

  Yuke Li, Xinfa Zhu, Hanzhao Li, ..., Zhifei Li, Lei Xie

Audio Editting

Datasets

Toolkits

Products

Misc

Misc

• Pushing the frontiers of audio generation