Data Augmentation For Children's Speech Recognition -- The "Ethiopian" System For The SLT 2021 Children Speech Recognition Challenge
This work addresses the domain-specific issue of improving speech recognition accuracy for children, which is incremental as it builds on existing techniques.
The paper tackled the problem of children's speech recognition by addressing the lack of training data through various data processing and augmentation techniques, achieving state-of-the-art results with 21.66% CER on Track 1 (4th place) and 16.53% CER on Track 2 (1st place) in the SLT 2021 challenge.
This paper presents the "Ethiopian" system for the SLT 2021 Children Speech Recognition Challenge. Various data processing and augmentation techniques are proposed to tackle children's speech recognition problem, especially the lack of the children's speech recognition training data issue. Detailed experiments are designed and conducted to show the effectiveness of each technique, across different speech recognition toolkits and model architectures. Step by step, we explain how we come up with our final system, which provides the state-of-the-art results in the SLT 2021 Children Speech Recognition Challenge, with 21.66% CER on the Track 1 evaluation set (4th place overall), and 16.53% CER on the Track 2 evaluation set (1st place overall). Post-challenge analysis shows that our system actually achieves 18.82% CER on the Track 1 evaluation set, but we submitted the wrong version to the challenge organizer for Track 1.