1. [Publications](/index.php/publications)
2. VoiceNoNG: Robust High-Quality Speech Editing Model without Hallucinations
 
 # VoiceNoNG: Robust High-Quality Speech Editing Model without Hallucinations

  ![Publication image](/sites/default/files/styles/wide/public/default_images/default.jpeg?itok=qUFsuJCP "Publication image")

 Voicebox and VoiceCraft are the current most representative models for non-autoregressive and autoregressive speech editing, respectively. Although both of them can generate high-quality speech edits, we identify their limitations: Voicebox is not good at editing speech with background audio, while VoiceCraft suffers from the hallucination-like problem. To maintain speech quality for varying audio scenarios and address the hallucination issue, we introduce VoiceNoNG, which combines the strengths of both model frameworks. VoiceNoNG utilizes a latent flow-matching framework to model the pre-quantization features of a neural codec. The vector quantizer in the neural codec provides additional robustness against minor prediction errors from the editing model, which enables VoiceNoNG to achieve state-of-the-art performance in both objective and subjective evaluations under diverse audio conditions.



 ## Authors



[Sung-Feng Huang](/index.php/person/sung-feng-huang)

Heng-Cheng Kuo (National Taiwan University)

Zhehuai Chen (NVIDIA)

Xuesong Yang (NVIDIA)

Pin-Jui Ku (NVIDIA)

Ante Jukić (NVIDIA)

[Huck Yang](/index.php/person/huck-yang)

Yu Tsao (Academia Sinica)

[Frank Wang](/index.php/person/frank-wang)

Hung-yi Lee (National Taiwan University)

[Szu-Wei Fu](/index.php/person/szu-wei-fu)

 

 

 ## Publication Date



Sunday, August 17, 2025

 

 ## Published in



[Interspeech 2025](https://www.interspeech2025.org/home)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence)

[Generative AI](/index.php/research-area/generative-ai)

[Speech Processing](/index.php/research-area/speech-processing)

 

 

 ## External Links



[Demo page](https://jasonswfu.github.io/NoNG-IS-/)