spoken-qa

DuplexJev 通过小型连接器将 ASR 编码器隐藏状态输入冻结 LLM，将每个多工决策表示为单一 token 分布而无需自回归解码，使 8 GPU 节点在约 0.1 秒内处理 80 个语音决策，同时在口语问答、说话人性别与情感识别上取得高精度。

This paper introduces VākQA, a Telugu spoken factoid question answering benchmark, and evaluates models using automated and human judges to address low-resource language challenges.