A GDPR-compliant Ecosystem for Speech Recognition with Transfer, Federated, and Evolutionary Learning

Automatic Speech Recognition (ASR) is playing a vital role in a wide range of real-world applications. However, Commercial ASR solutions are typically one-size-fits-all products and clients are inevitably faced with the risk of severe performance degradation in field test. Meanwhile, with new data regulations such as the European Union's General Data Protection Regulation (GDPR) coming into force, ASR vendors, which traditionally utilize the speech training data in a centralized approach, are becoming increasingly helpless to solve this problem, since accessing clients' speech data is prohibited. Here, we show that by seamlessly integrating three machine learning paradigms (i.e., Transfer learning, Federated learning, and Evolutionary learning (TFE)), we can successfully build a win-win ecosystem for ASR clients and vendors and solve all the aforementioned problems plaguing them. Through large-scale quantitative experiments, we show that with TFE, the clients can enjoy far better ASR solutions than the one-size-fits-all counterpart, and the vendors can exploit the abundance of clients' data to effectively refine their own ASR products.

Automated summary

Automatic Speech Recognition (ASR) is crucial in real-world applications, but commercial solutions often face performance degradation and data regulation issues. By integrating three machine learning paradigms, a win-win ecosystem is created for both clients and vendors, solving their problems effectively.