研究人员开发了一种新颖的自动语音识别方法，使用冻结的离散扩散语言模型，这与传统的自回归解码器不同。这种新方法在几个去噪步骤中并行地精炼整个文本记录。该模型是DiffusionGemma的音频原生接口，它使用冻结的Whisper编码器来获取声学特征，并在LibriSpeech test-clean基准测试上实现了6.6%的词错误率，大约在八个并行步骤中处理语音。 AI
影响 这项研究可能导致更高效和并行化的语音转录系统，从而可能改进实时应用。
排序理由 该集群描述了一篇详细介绍使用扩散语言模型进行语音识别的新颖方法的研究论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2607.13013v1 Announce Type: new Abstract: Automatic speech recognition is dominated by autoregressive decoders that emit one token at a time. We ask whether a discrete diffusion language model can transcribe speech instead, refining a whole transcript in parallel over a sma…
Automatic speech recognition is dominated by autoregressive decoders that emit one token at a time. We ask whether a discrete diffusion language model can transcribe speech instead, refining a whole transcript in parallel over a small number of denoising steps. We train an audio-…
Automatic speech recognition is dominated by autoregressive decoders that emit one token at a time. We ask whether a discrete diffusion language model can transcribe speech instead, refining a whole transcript in parallel over a small number of denoising steps. We train an audio-…