Automatic speech recognition for launch control center communication using recurrent neural networks with data augmentation and custom language model
This work solves transcription for NASA's launch control, enabling better information analysis, but is incremental as it applies existing methods to a specific domain.
The paper tackled automatic speech recognition for NASA's launch control center communications, addressing challenges like limited training data and specialized vocabulary, and demonstrated that data augmentation and custom language models improved accuracy.
Transcribing voice communications in NASA's launch control center is important for information utilization. However, automatic speech recognition in this environment is particularly challenging due to the lack of training data, unfamiliar words in acronyms, multiple different speakers and accents, and conversational characteristics of speaking. We used bidirectional deep recurrent neural networks to train and test speech recognition performance. We showed that data augmentation and custom language models can improve speech recognition accuracy. Transcribing communications from the launch control center will help the machine analyze information and accelerate knowledge generation.