论文标题

多域多设备ASR系统的统一建模

Unified Modeling of Multi-Domain Multi-Device ASR Systems

论文作者

Mitra, Soumyajit, Ray, Swayambhu Nath, Padi, Bharat, Sen, Arunasish, Bilgi, Raghavendra, Arsikere, Harish, Ghosh, Shalini, Srinivasamurthy, Ajay, Garimella, Sri

论文摘要

现代自动语音识别(ASR)系统通常使用特定于域模型的投资组合,以便在不同设备的不同用户话语类型中获得高精度。在本文中,我们提出了一种创新的方法,该方法将不同的人均每个设备模型整合到统一模型中,结合了域嵌入,域专家,专家的混合和对抗性培训。我们进行了仔细的消融研究,以显示每种创新的好处,从而有助于整体统一模型的准确性。实验表明,我们提出的统一建模方法实际上优于经过精心调整的每域模型,相对增长比基线模型高达10%,而参数数量可以忽略不计。

Modern Automatic Speech Recognition (ASR) systems often use a portfolio of domain-specific models in order to get high accuracy for distinct user utterance types across different devices. In this paper, we propose an innovative approach that integrates the different per-domain per-device models into a unified model, using a combination of domain embedding, domain experts, mixture of experts and adversarial training. We run careful ablation studies to show the benefit of each of these innovations in contributing to the accuracy of the overall unified model. Experiments show that our proposed unified modeling approach actually outperforms the carefully tuned per-domain models, giving relative gains of up to 10% over a baseline model with negligible increase in the number of parameters.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源