Step-Audio-EditX Technical Report
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911275833884672 |
|---|---|
| author | Yan, Chao Wu, Boyong Yang, Peng Tan, Pengfei Hu, Guoqiang Xie, Li Zhang, Yuxin Xiangyu Zhang Tian, Fei Yang, Xuerui Zhang, Xiangyu Jiang, Daxin Zhou, Shuchang Yu, Gang |
| author_facet | Yan, Chao Wu, Boyong Yang, Peng Tan, Pengfei Hu, Guoqiang Xie, Li Zhang, Yuxin Xiangyu Zhang Tian, Fei Yang, Xuerui Zhang, Xiangyu Jiang, Daxin Zhou, Shuchang Yu, Gang |
| contents | We present Step-Audio-EditX, the first open-source LLM-based audio model excelling at expressive and iterative audio editing encompassing emotion, speaking style, and paralinguistics alongside robust zero-shot text-to-speech (TTS) capabilities. Our core innovation lies in leveraging only large-margin synthetic data, which circumvents the need for embedding-based priors or auxiliary modules. This large-margin learning approach enables both iterative control and high expressivity across voices, and represents a fundamental pivot from the conventional focus on representation-level disentanglement. Evaluation results demonstrate that Step-Audio-EditX surpasses both MiniMax-2.6-hd and Doubao-Seed-TTS-2.0 in emotion editing and other fine-grained control tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_03601 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Step-Audio-EditX Technical Report Yan, Chao Wu, Boyong Yang, Peng Tan, Pengfei Hu, Guoqiang Xie, Li Zhang, Yuxin Xiangyu Zhang Tian, Fei Yang, Xuerui Zhang, Xiangyu Jiang, Daxin Zhou, Shuchang Yu, Gang Computation and Language Artificial Intelligence Human-Computer Interaction Sound Audio and Speech Processing We present Step-Audio-EditX, the first open-source LLM-based audio model excelling at expressive and iterative audio editing encompassing emotion, speaking style, and paralinguistics alongside robust zero-shot text-to-speech (TTS) capabilities. Our core innovation lies in leveraging only large-margin synthetic data, which circumvents the need for embedding-based priors or auxiliary modules. This large-margin learning approach enables both iterative control and high expressivity across voices, and represents a fundamental pivot from the conventional focus on representation-level disentanglement. Evaluation results demonstrate that Step-Audio-EditX surpasses both MiniMax-2.6-hd and Doubao-Seed-TTS-2.0 in emotion editing and other fine-grained control tasks. |
| title | Step-Audio-EditX Technical Report |
| topic | Computation and Language Artificial Intelligence Human-Computer Interaction Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2511.03601 |