通过可调深度循环变压器，让语音识别在测试时动态增加计算量提升准确率。
Test-Time Compute Scaling for ASR with Depth-Conditioned Looped Transformers
- 用循环结构共享权重，按需扩展推理深度以控制测试时计算量。
- 在LibriSpeech上随循环次数增加，错误率持续下降，接近更深模型性能。
- 适合需要灵活部署、追求高精度的语音识别场景，尤其对算力受限系统有用。
端到端语音识别系统通常在推理时使用固定深度的声学编码器，难以通过增加测试时计算量来提升识别效果而无需训练更大模型。一种自然的方法是重复使用共享的Transformer块，但我们发现简单的循环无法充分利用额外的计算资源。为此，我们提出LARM，一种深度可控的循环Transformer，将循环深度作为可调节的测试时计算轴。LARM结合稀疏CTC检查点、监督时钟嵌入、FiLM深度条件化和延迟软后验反馈，将循环结构划分为由隐状态精炼阶段分隔的识别检查点，使共享权重能在不同循环步骤中实现功能分化。在LibriSpeech数据集上，LARM随着推理循环次数增加，词错误率（WER）持续降低，性能达到与更深的非共享参数基线相当水平。结果表明，测试时计算扩展可从自回归语言建模延伸至连续的非自回归语音识别任务。
原文摘要 · Abstract (English)
End-to-end ASR systems typically use fixed-depth acoustic encoders at inference, making it difficult to trade additional test-time computation for improved recognition without training a larger model. A natural approach is to reuse a shared Transformer block recurrently, but we find that naive looping does not fully exploit additional recurrent compute. We introduce LARM, a depth-conditioned looped Transformer that turns recurrent encoder depth into a controllable test-time compute axis. LARM combines sparse CTC checkpoints, supervision-clock embeddings, FiLM depth conditioning, and delayed soft-posterior feedback. These components structure the loop into recognition checkpoints separated by latent refinement phases and allow shared weights to specialize across recurrent steps. On LibriSpeech, LARM improves WER as the number of inference loops increases and achieves performance competitive with deeper unshared-parameter baselines. Our results show that test-time compute scaling can extend beyond autoregressive language-model reasoning to continuous non-autoregressive speech recognition.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。