Transfer Learning for Speech Recognition on a Budget

Understand

End-to-end training of automated speech recognition (ASR) systems requires massive data and compute resources.

• We explore transfer learning based on model adaptation as an approach for training ASR models under constrained GPU memory, throughput and training data.
• We conduct several systematic experiments adapting a Wav2Letter convolutional neural network originally trained for English ASR to the German language.
• We show that this technique allows faster training on consumer-grade resources while requiring less training data in order to achieve the same accuracy, thereby lowering the cost of training ASR models in other languages.