Recent advancement in Automatic Speech Recognition (ASR) has produced large
AI models, which become impractical for deployment in mobile devices. Model
quantization is effective to produce compressed general-purpose models, however
such models may only be deployed to a restricted sub-domain of interest. We
show that ASR models can be personalized during quantization while relying on
just a small set of unlabelled samples from the target domain. To this end, we
propose myQASR, a mixed-precision quantization method that generates tailored
quantization schemes for diverse users under any memory requirement with no
fine-tuning. myQASR automatically evaluates the quantization sensitivity of
network layers by analysing the full-precision activation values. We are then
able to generate a personalised mixed-precision quantization scheme for any
pre-determined memory budget. Results for large-scale ASR models show how
myQASR improves performance for specific genders, languages, and speakers.

最近的自动语音识别（ASR）中取得的进展产生了大型 AI 模型，这些模型在移动设备上部署变得不切实际。模型量化可以产生压缩的通用模型，但这些模型可能只能在特定领域中部署。我们表明在量化过程中可以个性化地对 ASR 模型进行个性化调整，仅依赖于目标领域的少量未标记样本。为此，我们提出了 myQASR，一种混合精度量化方法，它可以在不需要微调的情况下为不同用户生成量化方案，以适应任何内存需求。myQASR 通过分析全精度激活值来自动评估网络层的量化灵敏度，我们能够为任何预定的内存预算生成个性化的混合精度量化方案。大规模 ASR 模型的结果表明 myQASR 如何提高特定性别、语言和说话者的性能。