paper-with-me

홈 › Papers

Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model

2025-06-10 · Ailin Huang, Bingxin Li, Bruce Wang, Boyong Wu, Chao Yan, Chengli Feng, Heng Wang, HongYu Zhou, Hongyuan Wang, Jingbei Li, Jianjian Sun, Joanna Wang, Mingrui Chen, Peng Liu, Ruihang Miao, Shilei Jiang, Tian Fei, Wang You, Xi Chen, Xuerui Yang, Yechang Huang, Yuxiang Zhang, Zheng Ge, Zheng Gong, Zhewei Huang, Zixin Zhang, Bin Wang, Bo Li, Buyun Ma, Changxin Miao, Changyi Wan, Chen Xu, Dapeng Shi, Dingyuan Hu, Enle Liu, Guanzhe Huang, Gulin Yan, Hanpeng Hu, Haonan Jia, Jiahao Gong, Jiaoren Wu, Jie Wu, Jie Yang, Junzhe Lin, Kaixiang Li, Lei Xia, Longlong Gu, Ming Li, Nie Hao, Ranchen Ming, Shaoliang Pang, SiQi Liu, Song Yuan, Tiancheng Cao, Wen Li, Wenqing He, Xu Zhao, Xuelin Zhang, Yanbo Yu, Yinmin Zhong, Yu Zhou, Yuanwei Liang, Yuanwei Lu, Yuxiang Yang, Zidong Yang, Zili Zhang, Binxing Jiao, Heung-Yeung Shum, Jiansheng Chen, Jing Li, Xiangyu Zhang, Xinhao Zhang, Yibo Zhu, Daxin Jiang, Shuchang Zhou, Chen Hu

Large Audio-Language Models (LALMs) have significantly advanced intelligent human-computer interaction, yet their reliance on text-based outputs limits their ability to generate natural speech responses directly, hindering seamless audio interactions. To address this, we introduce Step-Audio-AQAA, a fully end-to-end LALM designed for Audio Query-Audio Answer (AQAA) tasks. The model integrates a dual-codebook audio tokenizer for linguistic and semantic feature extraction, a 130-billion-parameter backbone LLM and a neural vocoder for high-fidelity speech synthesis. Our post-training approach employs interleaved token-output of text and audio to enhance semantic coherence and combines Direct Preference Optimization (DPO) with model merge to improve performance. Evaluations on the StepEval-Audio-360 benchmark demonstrate that Step-Audio-AQAA excels especially in speech control, outperforming the state-of-art LALMs in key areas. This work contributes a promising solution for end-to-end LALMs and highlights the critical role of token-based vocoder in enhancing overall performance for AQAA tasks.

📄 PDF Abstract BibTeX arXiv:2506.08967

Code (1)

stepfun-ai/step-audio pytorch

Tasks

Language ModelingLanguage ModellingSpeech Synthesis

Similar Papers 제목 키워드 기반

Step-Audio-EditX Technical Report

2025-11-05 · Chao Yan, Boyong Wu, Peng Yang, Pengfei Tan 외 arxiv

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-sp…

Step-Audio 2 Technical Report

2025-07-22 · Boyong Wu, Chao Yan, Chen Hu, Cheng Yi 외 arxiv

This paper presents Step-Audio 2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent audio encoder and reasoning-centric rei…

Reinforcement LearningSpeech Recognition

Real-time One-Step Diffusion-based Expressive Portrait Videos Generation

2024-12-18 · Hanzhong Guo, Hongwei Yi, Daquan Zhou, Alexander William Bergman 외

Latent diffusion models have made great strides in generating expressive portrait videos with accurate lip-sync and natural motion from a single reference image and audio input. However, these models are far from real-ti…

Video Generation

UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice

2025-09-25 · Sitong Cheng, Weizhen Bian, Xinsheng Wang, Ruibin Yuan 외 arxiv

The ultimate goal of expressive speech-to-speech translation (S2ST) is to accurately translate spoken content while preserving the speaker identity and emotional style. However, progress in this field is largely hindered…

Speech-to-Speech TranslationText to Speech

Do You Have Freestyle? Expressive Humanoid Locomotion via Audio Control

2025-12-29 · Zhe Li, Cheng Chi, Yangyang Wei, Boan Zhu 외 arxiv

Humans intuitively move to sound, but current humanoid robots lack expressive improvisational capabilities, confined to predefined motions or sparse commands. Generating motion from audio and then retargeting it to robot…