Tag
Qwen-Audio-3.1-ASR 技术报告介绍了一系列音频语言模型，在语音识别、说话人分离转录和通用音频理解方面较 Qwen-Audio-3.0-ASR 有显著提升，支持 30 种语言和 16 种汉语方言，并提供流式与非流式等多种部署变体。
inclusionAI 发布 Ming-3.0-audio-flash，一个 126B 总参数（每步激活 6.5B）的原生音频-语言 MoE 模型，支持中英文语音识别、语音问答、长音频理解、音频推理以及可选的语音合成输出，采用 MIT 许可证。
This paper presents the SEAR system for multilingual speech MCQ, achieving 90.92% accuracy on the MLC-SLM Challenge through segment-evidence-aware routing, supervised fine-tuning, and reinforcement learning.
FireRedAudio and FireRedTTS3 are AI models for unified audio understanding and generation, offering ASR, TTS, voice cloning, editing, and multilingual support with competitive benchmarks.
This paper introduces GigaChat Audio, a time-aware large audio language model that answers questions with explicit timestamps for up to 120 minutes of audio, using interleaved periodic time markers and synthetic supervision. The model achieves strong temporal grounding accuracy on benchmarks and the authors release model weights and datasets.
This paper introduces Audio-Interaction, a unified streaming audio model that combines offline task execution with real-time audio instruction following via an end-to-end framework. It proposes SoundFlow for the perceive-decide-respond loop and evaluates competitive performance across benchmarks.
StepAudio 2.5 is a unified audio-language model that achieves state-of-the-art results across ASR, TTS, and real-time spoken interaction by leveraging task-tailored reinforcement learning from human feedback to optimize shared representations.