Voice Memory for Agentic Speech Recognition
面向智能体语音识别的语音记忆
机构 * NVIDIA(英伟达)
AI总结 该研究提出仅推理方案Voice Memory,通过听者-思考者架构克制过度校正,在10个HyPoradise域上将加权词错误率降至7.52%,可跨校正器迁移且不增加推理参数。
Comments Preprint. Technical report and open source: https://huggingface.co/huckiyang/voice-memory