arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.09384eess.AScs.AI
收藏

MobileASR:一种面向手机用户语音个性化应用的资源感知设备端学习框架

MobileASR: A resource-aware on-device learning framework for user voice personalization applications on mobile phones

Indian Institute of Science(印度科学理工学院)

Zitha Sasindran, Harsha Yelchuri, Pooja Rao, T. V. Prabhakar

AI总结:

本文提出MobileASR框架,通过资源感知的子模型训练方法在手机上实现用户语音个性化ASR,平衡性能、训练时间与内存消耗,并在多品牌手机上验证有效性。

摘要:

我们描述了一种通过在手机上有效训练模型来开发用户语音个性化自动语音识别(ASR)模型的综合方法,允许用户数据和模型在本地存储和使用。为实现这一目标,我们提出了一种基于子模型的资源感知训练方法,该方法考虑了手机的RAM和电池能力。通过考虑评估指标和手机的资源约束,我们能够高效地执行训练并相应地停止该过程。为了模拟真实用户,我们使用了具有各种口音的说话者。整个设备端训练和评估框架随后在不同品牌的多种手机上进行了测试。我们表明,微调模型并选择正确的超参数值是在可实现的最低性能指标、设备端训练时间和内存消耗之间进行权衡。总体而言,我们的方法为开发个性化ASR模型提供了综合解决方案,同时利用了手机的能力,并平衡了准确性需求与资源约束。

英文摘要:

We describe a comprehensive methodology for developing user-voice personalized automatic speech recognition (ASR) models by effectively training models on mobile phones, allowing user data and models to be stored and used locally. To achieve this, we propose a resource-aware sub-model-based training approach that considers the RAM, and battery capabilities of mobile phones. By considering the evaluation metric and resource constraints of the mobile phones, we are able to perform efficient training and halt the process accordingly. To simulate real users, we use speakers with various accents. The entire on-device training and evaluation framework was then tested on various mobile phones across brands. We show that fine-tuning the models and selecting the right hyperparameter values is a trade-off between the lowest achievable performance metric, on-device training time, and memory consumption. Overall, our methodology offers a comprehensive solution for developing personalized ASR models while leveraging the capabilities of mobile phones, and balancing the need for accuracy with resource constraints.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑